@inproceedings{18061, abstract = {Mixture-of-Experts (MoE) architectures offer a general solution to the high inference costs of large language models (LLMs) via sparse routing, bringing faster and more accurate models, at the cost of massive parameter counts. For example, the SwitchTransformer-c2048 model has 1.6 trillion parameters, requiring 3.2TB of accelerator memory to run efficiently, which makes practical deployment challenging and expensive. In this paper, we present a solution to this memory problem, in form of a new compression and execution framework called QMoE. Specifically, QMoE consists of a scalable algorithm which accurately compresses trillion-parameter MoEs to less than 1 bit per parameter, in a custom format co-designed with bespoke GPU decoding kernels to facilitate efficient end-to-end compressed inference, with minor runtime overheads relative to uncompressed execution. Concretely, QMoE can compress the 1.6 trillion parameter SwitchTransformer-c2048 model to less than 160GB (20x compression, 0.8 bits per parameter) at only minor accuracy loss, in less than a day on a single GPU. This enables, for the first time, the execution of a trillion-parameter model on affordable commodity hardware, like a single server with 4x NVIDIA A6000 or 8x NVIDIA 3090 GPUs, at less than 5% runtime overhead relative to ideal uncompressed inference. The anonymized code is available at: github.com/mlsys24-qmoe/qmoe.}, author = {Frantar, Elias and Alistarh, Dan-Adrian}, booktitle = {Proceedings of Machine Learning and Systems}, location = {Santa Clara, CA, United States}, title = {{QMoE: Sub-1-bit compression of trillion parameter models}}, volume = {6}, year = {2024}, } @phdthesis{17465, abstract = {In the modern age of machine learning, artificial neural networks have become an integral part of many practical systems. One of the key ingredients of the success of the deep learning approach is recent computational advances which allowed the training of models with billions of parameters on large-scale data. Such over-parameterized and data-hungry regimes pose a challenge for the theoretical analysis of modern models since “classical” statistical wisdom is no longer applicable. In this view, it is paramount to extend or develop new machinery that will allow tackling the neural network analysis under new challenging asymptotic regimes, which is the focus of this thesis. Large neural network systems are usually optimized via “local” search algorithms, such as stochastic gradient descent (SGD). However, given the high-dimensional nature of the parameter space, it is a priori not clear why such a crude “local” approach works so remarkably well in practice. We take a step towards demystifying this phenomenon by showing that the landscape of the SGD training dynamics exhibits a few beneficial properties for the optimization. First, we show that along the SGD trajectory an over-parameterized network is dropout stable. The emergence of dropout stability allows to conclude that the minima found by SGD are connected via a continuous path of small loss. This in turn means that the high-dimensional landscape of the neural network optimization problem is provably not so unfavourable to gradient-based training, due to mode connectivity. Next, we show that SGD for an over-parameterized network tends to find solutions that are functionally more “simple”. This in turn means that the SGD minima are more robust, since a less complicated solution will less likely overfit the data. More formally, for a prototypical example of a wide two-layer ReLU network on a 1d regression task we show that the SGD algorithm is implicitly selective in its choice of an interpolating solution. Namely, at convergence the neural network implements a piece-wise linear function with the number of linear regions depending only on the amount of training data. This is in contrast to a “smooth”-like behaviour which one would expect given such a severe over-parameterization of the model. Diverging from the generic supervised setting of classification and regression problems, we analyze an auto-encoder model that is commonly used for representation learning and data compression. Despite the wide applicability of the auto-encoding paradigm, the theoretical understanding of their behaviour is limited even in the simplistic shallow case. The related work is restricted to extreme asymptotic regimes in which the auto-encoder is either severely over-parameterized or under-parameterized. In contrast, we provide a tight characterization for the 1-bit compression of Gaussian signals in the challenging proportional regime, i.e., the input dimension and the size of the compressed representation obey the same asymptotics. We also show that gradient-based methods are able to find a globally optimal solution and that the predictions made for Gaussian data extrapolate beyond - to the case of compression of natural images. Next, we relax the Gaussian assumption and study more structured input sources. We show that the shallow model is sometimes agnostic to the structure of the data vii which results in a Gaussian-like behaviour. We prove that making the decoding component slightly less shallow is already enough to escape the “curse” of Gaussian performance. }, author = {Shevchenko, Aleksandr}, issn = {2663-337X}, pages = {232}, publisher = {Institute of Science and Technology Austria}, title = {{High-dimensional limits in artificial neural networks}}, doi = {10.15479/at:ista:17465}, year = {2024}, } @inproceedings{17469, abstract = {Autoencoders are a prominent model in many empirical branches of machine learning and lossy data compression. However, basic theoretical questions remain unanswered even in a shallow two-layer setting. In particular, to what degree does a shallow autoencoder capture the structure of the underlying data distribution? For the prototypical case of the 1-bit compression of sparse Gaussian data, we prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. Namely, the performance of the algorithm is the same as if it was compressing a Gaussian source - with no sparsity. For general data distributions, we give evidence of a phase transition phenomenon in the shape of the gradient descent minimizer, as a function of the data sparsity: below the critical sparsity level, the minimizer is a rotation taken uniformly at random (just like in the compression of non-sparse data); above the critical sparsity, the minimizer is the identity (up to a permutation). Finally, by exploiting a connection with approximate message passing algorithms, we show how to improve upon Gaussian performance for the compression of sparse data: adding a denoising function to a shallow architecture already reduces the loss provably, and a suitable multi-layer decoder leads to a further improvement. We validate our findings on image datasets, such as CIFAR-10 and MNIST.}, author = {Kögler, Kevin and Shevchenko, Aleksandr and Hassani, Hamed and Mondelli, Marco}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, location = {Vienna, Austria}, pages = {24964--25015}, publisher = {ML Research Press}, title = {{Compression of structured data with autoencoders: Provable benefit of nonlinearities and depth}}, volume = {235}, year = {2024}, } @article{12330, abstract = {The design and implementation of efficient concurrent data structures has seen significant attention. However, most of this work has focused on concurrent data structures providing good worst-case guarantees, although, in real workloads, objects are often accessed at different rates. Efficient distribution-adaptive data structures, such as splay-trees, are known in the sequential case; however, they often are hard to translate efficiently to the concurrent case. We investigate distribution-adaptive concurrent data structures, and propose a new design called the splay-list. At a high level, the splay-list is similar to a standard skip-list, with the key distinction that the height of each element adapts dynamically to its access rate: popular elements “move up,” whereas rarely-accessed elements decrease in height. We show that the splay-list provides order-optimal amortized complexity bounds for a subset of operations, while being amenable to efficient concurrent implementation. Experiments show that the splay-list can leverage distribution-adaptivity for performance, and can outperform the only previously-known distribution-adaptive concurrent design in certain workloads.}, author = {Aksenov, Vitalii and Alistarh, Dan-Adrian and Drozdova, Alexandra and Mohtashami, Amirkeivan}, issn = {1432-0452}, journal = {Distributed Computing}, pages = {395--418}, publisher = {Springer Nature}, title = {{The splay-list: A distribution-adaptive concurrent skip-list}}, doi = {10.1007/s00446-022-00441-x}, volume = {36}, year = {2023}, } @article{12566, abstract = {Approximate agreement is one of the few variants of consensus that can be solved in a wait-free manner in asynchronous systems where processes communicate by reading and writing to shared memory. In this work, we consider a natural generalisation of approximate agreement on arbitrary undirected connected graphs. Each process is given a node of the graph as input and, if non-faulty, must output a node such that – all the outputs are within distance 1 of one another, and – each output value lies on a shortest path between two input values. From prior work, it is known that there is no wait-free algorithm among processes for this problem on any cycle of length , by reduction from 2-set agreement (Castañeda et al., 2018). In this work, we investigate the solvability of this task on general graphs. We give a new, direct proof of the impossibility of approximate agreement on cycles of length , via a generalisation of Sperner's Lemma to convex polygons. We also extend the reduction from 2-set agreement to a larger class of graphs, showing that approximate agreement on these graphs is unsolvable. On the positive side, we present a wait-free algorithm for a different class of graphs, which properly contains the class of chordal graphs.}, author = {Alistarh, Dan-Adrian and Ellen, Faith and Rybicki, Joel}, issn = {0304-3975}, journal = {Theoretical Computer Science}, number = {2}, publisher = {Elsevier}, title = {{Wait-free approximate agreement on graphs}}, doi = {10.1016/j.tcs.2023.113733}, volume = {948}, year = {2023}, } @inproceedings{12735, abstract = {Asynchronous programming has gained significant popularity over the last decade: support for this programming pattern is available in many popular languages via libraries and native language implementations, typically in the form of coroutines or the async/await construct. Instead of programming via shared memory, this concept assumes implicit synchronization through message passing. The key data structure enabling such communication is the rendezvous channel. Roughly, a rendezvous channel is a blocking queue of size zero, so both send(e) and receive() operations wait for each other, performing a rendezvous when they meet. To optimize the message passing pattern, channels are usually equipped with a fixed-size buffer, so sends do not suspend and put elements into the buffer until its capacity is exceeded. This primitive is known as a buffered channel. This paper presents a fast and scalable algorithm for both rendezvous and buffered channels. Similarly to modern queues, our solution is based on an infinite array with two positional counters for send(e) and receive() operations, leveraging the unconditional Fetch-And-Add instruction to update them. Yet, the algorithm requires non-trivial modifications of this classic pattern, in order to support the full channel semantics, such as buffering and cancellation of waiting requests. We compare the performance of our solution to that of the Kotlin implementation, as well as against other academic proposals, showing up to 9.8× speedup. To showcase its expressiveness and performance, we also integrated the proposed algorithm into the standard Kotlin Coroutines library, replacing the previous channel implementations.}, author = {Koval, Nikita and Alistarh, Dan-Adrian and Elizarov, Roman}, booktitle = {Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming}, isbn = {9798400700156}, location = {Montreal, QC, Canada}, pages = {107--118}, publisher = {Association for Computing Machinery}, title = {{Fast and scalable channels in Kotlin Coroutines}}, doi = {10.1145/3572848.3577481}, year = {2023}, } @misc{12736, abstract = {Although a wide variety of handcrafted concurrent data structures have been proposed, there is considerable interest in universal approaches (Universal Constructions or UCs) for building concurrent data structures. UCs (semi-)automatically convert a sequential data structure into a concurrent one. The simplest approach uses locks [3, 6] that protect a sequential data structure and allow only one process to access it at a time. However, the resulting data structure is blocking. Most work on UCs instead focuses on obtaining non-blocking progress guarantees such as obstruction-freedom, lock-freedom or wait-freedom. Many non-blocking UCs have appeared. Key examples include the seminal wait-free UC [2] by Herlihy, a NUMA-aware UC [10] by Yi et al., and an efficient UC for large objects [1] by Fatourou et al.}, author = {Aksenov, Vitaly and Brown, Trevor A and Fedorov, Alexander and Kokorin, Ilya}, booktitle = {Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming}, isbn = {9798400700156}, location = {Montreal, QB, Canada}, pages = {438--440}, publisher = {Association for Computing Machinery}, title = {{Unexpected scaling in path copying trees}}, doi = {10.1145/3572848.3577512}, year = {2023}, } @inproceedings{13053, abstract = {Deep neural networks (DNNs) often have to be compressed, via pruning and/or quantization, before they can be deployed in practical settings. In this work we propose a new compression-aware minimizer dubbed CrAM that modifies the optimization step in a principled way, in order to produce models whose local loss behavior is stable under compression operations such as pruning. Thus, dense models trained via CrAM should be compressible post-training, in a single step, without significant accuracy loss. Experimental results on standard benchmarks, such as residual networks for ImageNet classification and BERT models for language modelling, show that CrAM produces dense models that can be more accurate than the standard SGD/Adam-based baselines, but which are stable under weight pruning: specifically, we can prune models in one-shot to 70-80% sparsity with almost no accuracy loss, and to 90% with reasonable (∼1%) accuracy loss, which is competitive with gradual compression methods. Additionally, CrAM can produce sparse models which perform well for transfer learning, and it also works for semi-structured 2:4 pruning patterns supported by GPU hardware. The code for reproducing the results is available at this https URL .}, author = {Peste, Elena-Alexandra and Vladu, Adrian and Kurtic, Eldar and Lampert, Christoph and Alistarh, Dan-Adrian}, booktitle = {11th International Conference on Learning Representations }, location = {Kigali, Rwanda }, publisher = {OpenReview}, title = {{CrAM: A Compression-Aware Minimizer}}, year = {2023}, } @inproceedings{13262, abstract = {Determining the degree of inherent parallelism in classical sequential algorithms and leveraging it for fast parallel execution is a key topic in parallel computing, and detailed analyses are known for a wide range of classical algorithms. In this paper, we perform the first such analysis for the fundamental Union-Find problem, in which we are given a graph as a sequence of edges, and must maintain its connectivity structure under edge additions. We prove that classic sequential algorithms for this problem are well-parallelizable under reasonable assumptions, addressing a conjecture by [Blelloch, 2017]. More precisely, we show via a new potential argument that, under uniform random edge ordering, parallel union-find operations are unlikely to interfere: T concurrent threads processing the graph in parallel will encounter memory contention O(T2 · log |V| · log |E|) times in expectation, where |E| and |V| are the number of edges and nodes in the graph, respectively. We leverage this result to design a new parallel Union-Find algorithm that is both internally deterministic, i.e., its results are guaranteed to match those of a sequential execution, but also work-efficient and scalable, as long as the number of threads T is O(|E|1 over 3 - ε), for an arbitrarily small constant ε > 0, which holds for most large real-world graphs. We present lower bounds which show that our analysis is close to optimal, and experimental results suggesting that the performance cost of internal determinism is limited.}, author = {Fedorov, Alexander and Hashemi, Diba and Nadiradze, Giorgi and Alistarh, Dan-Adrian}, booktitle = {Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures}, isbn = {9781450395458}, location = {Orlando, FL, United States}, pages = {261--271}, publisher = {Association for Computing Machinery}, title = {{Provably-efficient and internally-deterministic parallel Union-Find}}, doi = {10.1145/3558481.3591082}, year = {2023}, } @article{14364, abstract = {We introduce extension-based proofs, a class of impossibility proofs that includes valency arguments. They are modelled as an interaction between a prover and a protocol. Using proofs based on combinatorial topology, it has been shown that it is impossible to deterministically solve -set agreement among processes or approximate agreement on a cycle of length 4 among processes in a wait-free manner in asynchronous models where processes communicate using objects that can be constructed from shared registers. However, it was unknown whether proofs based on simpler techniques were possible. We show that these impossibility results cannot be obtained by extension-based proofs in the iterated snapshot model and, hence, extension-based proofs are limited in power.}, author = {Alistarh, Dan-Adrian and Aspnes, James and Ellen, Faith and Gelashvili, Rati and Zhu, Leqi}, issn = {1095-7111}, journal = {SIAM Journal on Computing}, number = {4}, pages = {913--944}, publisher = {Society for Industrial and Applied Mathematics}, title = {{Why extension-based proofs fail}}, doi = {10.1137/20M1375851}, volume = {52}, year = {2023}, } @inproceedings{14460, abstract = {We provide an efficient implementation of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and common layer types (e.g., convolutional or linear). We provide a fast vectorized implementation on commodity CPUs, and show that it can yield speedups in end-to-end runtime experiments, both in transfer learning using already-sparsified networks, and in training sparse networks from scratch. Thus, our results provide the first support for sparse training on commodity hardware.}, author = {Nikdan, Mahdi and Pegolotti, Tommaso and Iofinova, Eugenia B and Kurtic, Eldar and Alistarh, Dan-Adrian}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, issn = {2640-3498}, location = {Honolulu, Hawaii, HI, United States}, pages = {26215--26227}, publisher = {ML Research Press}, title = {{SparseProp: Efficient sparse backpropagation for faster training of neural networks at the edge}}, volume = {202}, year = {2023}, } @inproceedings{14461, abstract = {Communication-reduction techniques are a popular way to improve scalability in data-parallel training of deep neural networks (DNNs). The recent emergence of large language models such as GPT has created the need for new approaches to exploit data-parallelism. Among these, fully-sharded data parallel (FSDP) training is highly popular, yet it still encounters scalability bottlenecks. One reason is that applying compression techniques to FSDP is challenging: as the vast majority of the communication involves the model’s weights, direct compression alters convergence and leads to accuracy loss. We present QSDP, a variant of FSDP which supports both gradient and weight quantization with theoretical guarantees, is simple to implement and has essentially no overheads. To derive QSDP we prove that a natural modification of SGD achieves convergence even when we only maintain quantized weights, and thus the domain over which we train consists of quantized points and is, therefore, highly non-convex. We validate this approach by training GPT-family models with up to 1.3 billion parameters on a multi-node cluster. Experiments show that QSDP preserves model accuracy, while completely removing the communication bottlenecks of FSDP, providing end-to-end speedups of up to 2.2x.}, author = {Markov, Ilia and Vladu, Adrian and Guo, Qi and Alistarh, Dan-Adrian}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, issn = {2640-3498}, location = {Honolulu, Hawaii, HI, United States}, pages = {24020--24044}, publisher = {ML Research Press}, title = {{Quantized distributed training of large models with convergence guarantees}}, volume = {202}, year = {2023}, } @article{14815, abstract = {In the last few years, various communication compression techniques have emerged as an indispensable tool helping to alleviate the communication bottleneck in distributed learning. However, despite the fact biased compressors often show superior performance in practice when compared to the much more studied and understood unbiased compressors, very little is known about them. In this work we study three classes of biased compression operators, two of which are new, and their performance when applied to (stochastic) gradient descent and distributed (stochastic) gradient descent. We show for the first time that biased compressors can lead to linear convergence rates both in the single node and distributed settings. We prove that distributed compressed SGD method, employed with error feedback mechanism, enjoys the ergodic rate O(δLexp[−μKδL]+(C+δD)Kμ), where δ≥1 is a compression parameter which grows when more compression is applied, L and μ are the smoothness and strong convexity constants, C captures stochastic gradient noise (C=0 if full gradients are computed on each node) and D captures the variance of the gradients at the optimum (D=0 for over-parameterized models). Further, via a theoretical study of several synthetic and empirical distributions of communicated gradients, we shed light on why and by how much biased compressors outperform their unbiased variants. Finally, we propose several new biased compressors with promising theoretical guarantees and practical performance.}, author = {Beznosikov, Aleksandr and Horvath, Samuel and Richtarik, Peter and Safaryan, Mher}, issn = {1533-7928}, journal = {Journal of Machine Learning Research}, pages = {1--50}, publisher = {Journal of Machine Learning Research}, title = {{On biased compression for distributed learning}}, volume = {24}, year = {2023}, } @article{13179, abstract = {Writing concurrent code that is both correct and efficient is notoriously difficult. Thus, programmers often prefer to use synchronization abstractions, which render code simpler and easier to reason about. Despite a wealth of work on this topic, there is still a gap between the rich semantics provided by synchronization abstractions in modern programming languages—specifically, fair FIFO ordering of synchronization requests and support for abortable operations—and frameworks for implementing it correctly and efficiently. Supporting such semantics is critical given the rising popularity of constructs for asynchronous programming, such as coroutines, which abort frequently and are cheaper to suspend and resume compared to native threads. This paper introduces a new framework called CancellableQueueSynchronizer (CQS), which enables simple yet efficient implementations of a wide range of fair and abortable synchronization primitives: mutexes, semaphores, barriers, count-down latches, and blocking pools. Our main contribution is algorithmic, as implementing both fairness and abortability efficiently at this level of generality is non-trivial. Importantly, all our algorithms, including the CQS framework and the primitives built on top of it, come with formal proofs in the Iris framework for Coq for many of their properties. These proofs are modular, so it is easy to show correctness for new primitives implemented on top of CQS. From a practical perspective, implementation of CQS for native threads on the JVM improves throughput by up to two orders of magnitude over Java’s AbstractQueuedSynchronizer, the only practical abstraction offering similar semantics. Further, we successfully integrated CQS as a core component of the popular Kotlin Coroutines library, validating the framework’s practical impact and expressiveness in a real-world environment. In sum, CancellableQueueSynchronizer is the first framework to combine expressiveness with formal guarantees and solid practical performance. Our approach should be extensible to other languages and families of synchronization primitives.}, author = {Koval, Nikita and Khalanskiy, Dmitry and Alistarh, Dan-Adrian}, issn = {2475-1421}, journal = {Proceedings of the ACM on Programming Languages}, publisher = {Association for Computing Machinery}, title = {{CQS: A formally-verified framework for fair and abortable synchronization}}, doi = {10.1145/3591230}, volume = {7}, year = {2023}, } @inbook{19983, abstract = {The sinkless orientation problem plays a key role in understanding the foundations of distributed computing. The problem can be used to separate two fundamental models of distributed graph algorithms, LOCAL and SLOCAL: the locality of sinkless orientation is Ω(log n) in the deterministic LOCAL model and O(log log n) in the deterministic SLOCAL model. Both of these results are known by prior work, but here we give new simple, self-contained proofs for them.}, author = {Balliu, Alkida and Korhonen, Janne and Kuhn, Fabian and Lievonen, Henrik and Olivetti, Dennis and Pai, Shreyas and Paz, Ami and Rybicki, Joel and Schmid, Stefan and Studený, Jan and Suomela, Jukka and Uitto, Jara}, booktitle = {Symposium on Simplicity in Algorithms}, location = {Florence, Italy}, pages = {175--191}, publisher = {Society for Industrial and Applied Mathematics}, title = {{Sinkless Orientation Made Simple}}, doi = {10.1137/1.9781611977585.ch17}, year = {2023}, } @inproceedings{15363, abstract = {Knowledge distillation is a popular approach for enhancing the performance of "student" models, with lower representational capacity, by taking advantage of more powerful "teacher" models. Despite its apparent simplicity, the underlying mechanics behind knowledge distillation (KD) are not yet fully understood. In this work, we shed new light on the inner workings of this method, by examining it from an optimization perspective. Specifically, we show that, in the context of linear and deep linear models, KD can be interpreted as a novel type of stochastic variance reduction mechanism. We provide a detailed convergence analysis of the resulting dynamics, which hold under standard assumptions for both strongly-convex and non-convex losses, showing that KD acts as a form of \emph{partial variance reduction}, which can reduce the stochastic gradient noise, but may not eliminate it completely, depending on the properties of the teacher'' model. Our analysis puts further emphasis on the need for careful parametrization of KD, in particular w.r.t. the weighting of the distillation loss, and is validated empirically on both linear models and deep neural networks.}, author = {Safaryan, Mher and Peste, Elena-Alexandra and Alistarh, Dan-Adrian}, booktitle = {36th Conference on Neural Information Processing Systems}, issn = {1049-5258}, location = {New Orleans, LA, United States}, publisher = {Neural Information Processing Systems Foundation}, title = {{Knowledge distillation performs partial variance reduction}}, volume = {36}, year = {2023}, } @inproceedings{14260, abstract = {This paper presents Lincheck, a new practical and user-friendly framework for testing concurrent algorithms on the Java Virtual Machine (JVM). Lincheck provides a simple and declarative way to write concurrent tests: instead of describing how to perform the test, users specify what to test by declaring all the operations to examine; the framework automatically handles the rest. As a result, tests written with Lincheck are concise and easy to understand. The framework automatically generates a set of concurrent scenarios, examines them using stress-testing or bounded model checking, and verifies that the results of each invocation are correct. Notably, if an error is detected via model checking, Lincheck provides an easy-to-follow trace to reproduce it, significantly simplifying the bug investigation. To the best of our knowledge, Lincheck is the first production-ready tool on the JVM that offers such a simple way of writing concurrent tests, without requiring special skills or expertise. We successfully integrated Lincheck in the development process of several large projects, such as Kotlin Coroutines, and identified new bugs in popular concurrency libraries, such as a race in Java’s standard ConcurrentLinkedDeque and a liveliness bug in Java’s AbstractQueuedSynchronizer framework, which is used in most of the synchronization primitives. We believe that Lincheck can significantly improve the quality and productivity of concurrent algorithms research and development and become the state-of-the-art tool for checking their correctness.}, author = {Koval, Nikita and Fedorov, Alexander and Sokolova, Maria and Tsitelov, Dmitry and Alistarh, Dan-Adrian}, booktitle = {35th International Conference on Computer Aided Verification}, isbn = {9783031377051}, issn = {1611-3349}, location = {Paris, France}, pages = {156--169}, publisher = {Springer Nature}, title = {{Lincheck: A practical framework for testing concurrent data structures on JVM}}, doi = {10.1007/978-3-031-37706-8_8}, volume = {13964}, year = {2023}, } @misc{14995, abstract = {Lincheck is a new practical and user-friendly framework for testing concurrent data structures on the Java Virtual Machine (JVM). It provides a simple and declarative way to write concurrent tests. Instead of describing how to perform the test, users specify what to test by declaring all the operations to examine; the framework automatically handles the rest. As a result, tests written with Lincheck are concise and easy to understand. The artifact presents a collection of Lincheck tests that discover new bugs in popular libraries and implementations from the concurrency literature -- they are listed in Table 1, Section 3. To evaluate the performance of Lincheck analysis, the collection of tests also includes those which check correct data structures and, thus, always succeed. Similarly to Table 2, Section 3, the experiments demonstrate the reasonable time to perform a test. Finally, Lincheck provides user-friendly output with an easy-to-follow trace to reproduce a detected error, significantly simplifying further investigation.}, author = {Koval, Nikita and Fedorov, Alexander and Sokolova, Maria and Tsitelov, Dmitry and Alistarh, Dan-Adrian}, publisher = {Zenodo}, title = {{Lincheck: A practical framework for testing concurrent data structures on JVM}}, doi = {10.5281/ZENODO.7877757}, year = {2023}, } @inproceedings{14771, abstract = {Pruning—that is, setting a significant subset of the parameters of a neural network to zero—is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate bias in the output of the compressed model. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood. In this work, we systematically investigate and characterize this phenomenon in Convolutional Neural Networks for computer vision. First, we show that it is in fact possible to obtain highly-sparse models, e.g. with less than 10% remaining weights, which do not decrease in accuracy nor substantially increase in bias when compared to dense models. At the same time, we also find that, at higher sparsities, pruned models exhibit higher uncertainty in their outputs, as well as increased correlations, which we directly link to increased bias. We propose easy-to-use criteria which, based only on the uncompressed model, establish whether bias will increase with pruning, and identify the samples most susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias.}, author = {Iofinova, Eugenia B and Peste, Elena-Alexandra and Alistarh, Dan-Adrian}, booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {Vancouver, BC, Canada}, pages = {24364--24373}, publisher = {IEEE}, title = {{Bias in pruned vision models: In-depth analysis and countermeasures}}, doi = {10.1109/cvpr52729.2023.02334}, year = {2023}, } @inproceedings{17378, abstract = {Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically, due to their massive size, even inference for large, highly-accurate GPT models may require multiple performant GPUs, which limits the usability of such models. While there is emerging work on relieving this pressure via model compression, the applicability and performance of existing compression techniques is limited by the scale and complexity of GPT models. In this paper, we address this challenge, and propose OPTQ, a new one-shot weight quantization method based on approximate second-order information, that is both highly-accurate and highly-efficient. Specifically, OPTQ can quantize GPT models with 175 billion parameters in approximately four GPU hours, reducing the bitwidth down to 3 or 4 bits per weight, with negligible accuracy degradation relative to the uncompressed baseline. Our method more than doubles the compression gains relative to previously-proposed one-shot quantization methods, preserving accuracy, allowing us for the first time to execute an 175 billion-parameter model inside a single GPU for generative inference. Moreover, we also show that our method can still provide reasonable accuracy in the extreme quantization regime, in which weights are quantized to 2-bit or even ternary quantization levels. We show experimentally that these improvements can be leveraged for end-to-end inference speedups over FP16, of around 3.25x when using high-end GPUs (NVIDIA A100) and 4.5x when using more cost-effective ones (NVIDIA A6000). The implementation is available at https://github.com/IST-DASLab/gptq.}, author = {Frantar, Elias and Ashkboos, Saleh and Hoefler, Torsten and Alistarh, Dan-Adrian}, booktitle = {11th International Conference on Learning Representations }, location = {Kigali, Rwanda}, publisher = {International Conference on Learning Representations}, title = {{OPTQ: Accurate post-training quantization for generative pre-trained transformers}}, year = {2023}, }