@phdthesis{9418, abstract = {Deep learning is best known for its empirical success across a wide range of applications spanning computer vision, natural language processing and speech. Of equal significance, though perhaps less known, are its ramifications for learning theory: deep networks have been observed to perform surprisingly well in the high-capacity regime, aka the overfitting or underspecified regime. Classically, this regime on the far right of the bias-variance curve is associated with poor generalisation; however, recent experiments with deep networks challenge this view. This thesis is devoted to investigating various aspects of underspecification in deep learning. First, we argue that deep learning models are underspecified on two levels: a) any given training dataset can be fit by many different functions, and b) any given function can be expressed by many different parameter configurations. We refer to the second kind of underspecification as parameterisation redundancy and we precisely characterise its extent. Second, we characterise the implicit criteria (the inductive bias) that guide learning in the underspecified regime. Specifically, we consider a nonlinear but tractable classification setting, and show that given the choice, neural networks learn classifiers with a large margin. Third, we consider learning scenarios where the inductive bias is not by itself sufficient to deal with underspecification. We then study different ways of ‘tightening the specification’: i) In the setting of representation learning with variational autoencoders, we propose a hand- crafted regulariser based on mutual information. ii) In the setting of binary classification, we consider soft-label (real-valued) supervision. We derive a generalisation bound for linear networks supervised in this way and verify that soft labels facilitate fast learning. Finally, we explore an application of soft-label supervision to the training of multi-exit models.}, author = {Bui Thi Mai, Phuong}, issn = {2663-337X}, pages = {125}, publisher = {Institute of Science and Technology Austria}, title = {{Underspecification in deep learning}}, doi = {10.15479/AT:ISTA:9418}, year = {2021}, } @inproceedings{9416, abstract = {We study the inductive bias of two-layer ReLU networks trained by gradient flow. We identify a class of easy-to-learn (`orthogonally separable') datasets, and characterise the solution that ReLU networks trained on such datasets converge to. Irrespective of network width, the solution turns out to be a combination of two max-margin classifiers: one corresponding to the positive data subset and one corresponding to the negative data subset. The proof is based on the recently introduced concept of extremal sectors, for which we prove a number of properties in the context of orthogonal separability. In particular, we prove stationarity of activation patterns from some time onwards, which enables a reduction of the ReLU network to an ensemble of linear subnetworks.}, author = {Bui Thi Mai, Phuong and Lampert, Christoph}, booktitle = {9th International Conference on Learning Representations}, location = {Virtual}, title = {{The inductive bias of ReLU networks on orthogonally separable data}}, year = {2021}, } @unpublished{8063, abstract = {We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from each other and from the background; unlike prior works, it explicitly represents the 2D position and depth of each object, as well as an embedding of its segmentation mask and appearance. The model can be trained from images alone in a purely unsupervised fashion without the need for object masks or depth information. Moreover, it always generates complete objects, even though a significant fraction of training images contain occlusions. Finally, we show that our model can infer decompositions of novel images into their constituent objects, including accurate prediction of depth ordering and segmentation of occluded parts.}, author = {Anciukevicius, Titas and Lampert, Christoph and Henderson, Paul M}, booktitle = {arXiv}, title = {{Object-centric image generation with factored depths, locations, and appearances}}, doi = {10.48550/arXiv.2004.00642}, year = {2020}, } @inproceedings{8186, abstract = {Numerous methods have been proposed for probabilistic generative modelling of 3D objects. However, none of these is able to produce textured objects, which renders them of limited use for practical tasks. In this work, we present the first generative model of textured 3D meshes. Training such a model would traditionally require a large dataset of textured meshes, but unfortunately, existing datasets of meshes lack detailed textures. We instead propose a new training methodology that allows learning from collections of 2D images without any 3D information. To do so, we train our model to explain a distribution of images by modelling each image as a 3D foreground object placed in front of a 2D background. Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set. A well-known problem when generating meshes with deep networks is the emergence of self-intersections, which are problematic for many use-cases. As a second contribution we therefore introduce a new generation process for 3D meshes that guarantees no self-intersections arise, based on the physical intuition that faces should push one another out of the way as they move. We conduct extensive experiments on our approach, reporting quantitative and qualitative results on both synthetic data and natural images. These show our method successfully learns to generate plausible and diverse textured 3D samples for five challenging object classes.}, author = {Henderson, Paul M and Tsiminaki, Vagia and Lampert, Christoph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {Virtual}, pages = {7498--7507}, publisher = {IEEE}, title = {{Leveraging 2D data to learn textured 3D mesh generation}}, doi = {10.1109/CVPR42600.2020.00752}, year = {2020}, } @inproceedings{8188, abstract = {A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects. We conduct detailed experiments on two datasets, going beyond the visual complexity supported by state-of-the-art generative approaches. We evaluate our method on depth-prediction and 3D object detection---tasks which cannot be addressed by those earlier works---and show it out-performs them even on 2D instance segmentation and tracking.}, author = {Henderson, Paul M and Lampert, Christoph}, booktitle = {34th Conference on Neural Information Processing Systems}, isbn = {9781713829546}, location = {Vancouver, Canada}, pages = {3106–3117}, publisher = {Neural Information Processing Systems Foundation}, title = {{Unsupervised object-centric video generation and decomposition in 3D}}, volume = {33}, year = {2020}, } @article{6944, abstract = {We study the problem of automatically detecting if a given multi-class classifier operates outside of its specifications (out-of-specs), i.e. on input data from a different distribution than what it was trained for. This is an important problem to solve on the road towards creating reliable computer vision systems for real-world applications, because the quality of a classifier’s predictions cannot be guaranteed if it operates out-of-specs. Previously proposed methods for out-of-specs detection make decisions on the level of single inputs. This, however, is insufficient to achieve low false positive rate and high false negative rates at the same time. In this work, we describe a new procedure named KS(conf), based on statistical reasoning. Its main component is a classical Kolmogorov–Smirnov test that is applied to the set of predicted confidence values for batches of samples. Working with batches instead of single samples allows increasing the true positive rate without negatively affecting the false positive rate, thereby overcoming a crucial limitation of single sample tests. We show by extensive experiments using a variety of convolutional network architectures and datasets that KS(conf) reliably detects out-of-specs situations even under conditions where other tests fail. It furthermore has a number of properties that make it an excellent candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with any classifier that outputs confidence scores, and requires no a priori knowledge about how the data distribution could change.}, author = {Sun, Rémy and Lampert, Christoph}, issn = {1573-1405}, journal = {International Journal of Computer Vision}, number = {4}, pages = {970--995}, publisher = {Springer Nature}, title = {{KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications}}, doi = {10.1007/s11263-019-01232-x}, volume = {128}, year = {2020}, } @article{6952, abstract = {We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches rely on 3D supervision, annotation of 2D images with keypoints or poses, and/or training with multiple views of each object instance. Our framework is very general: it can be trained in similar settings to existing approaches, while also supporting weaker supervision. Importantly, it can be trained purely from 2D images, without pose annotations, and with only a single view per instance. We employ meshes as an output representation, instead of voxels used in most prior work. This allows us to reason over lighting parameters and exploit shading information during training, which previous 2D-supervised methods cannot. Thus, our method can learn to generate and reconstruct concave object classes. We evaluate our approach in various settings, showing that: (i) it learns to disentangle shape from pose and lighting; (ii) using shading in the loss improves performance compared to just silhouettes; (iii) when using a standard single white light, our model outperforms state-of-the-art 2D-supervised methods, both with and without pose supervision, thanks to exploiting shading cues; (iv) performance improves further when using multiple coloured lights, even approaching that of state-of-the-art 3D-supervised methods; (v) shapes produced by our model capture smooth surfaces and fine details better than voxel-based approaches; and (vi) our approach supports concave classes such as bathtubs and sofas, which methods based on silhouettes cannot learn.}, author = {Henderson, Paul M and Ferrari, Vittorio}, issn = {1573-1405}, journal = {International Journal of Computer Vision}, pages = {835--854}, publisher = {Springer Nature}, title = {{Learning single-image 3D reconstruction by generative modelling of shape, pose and shading}}, doi = {10.1007/s11263-019-01219-8}, volume = {128}, year = {2020}, } @inproceedings{8724, abstract = {We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing and collaborative learning paradigms. Specifically, we analyze the situation in which a learning system obtains datasets from multiple sources, some of which might be biased or even adversarially perturbed. It is known that in the single-source case, an adversary with the power to corrupt a fixed fraction of the training data can prevent PAC-learnability, that is, even in the limit of infinitely much training data, no learning system can approach the optimal test error. In this work we show that, surprisingly, the same is not true in the multi-source setting, where the adversary can arbitrarily corrupt a fixed fraction of the data sources. Our main results are a generalization bound that provides finite-sample guarantees for this learning setting, as well as corresponding lower bounds. Besides establishing PAC-learnability our results also show that in a cooperative learning setting sharing data with other parties has provable benefits, even if some participants are malicious. }, author = {Konstantinov, Nikola H and Frantar, Elias and Alistarh, Dan-Adrian and Lampert, Christoph}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, issn = {2640-3498}, location = {Online}, pages = {5416--5425}, publisher = {ML Research Press}, title = {{On the sample complexity of adversarial multi-source PAC learning}}, volume = {119}, year = {2020}, } @inproceedings{7481, abstract = {We address the following question: How redundant is the parameterisation of ReLU networks? Specifically, we consider transformations of the weight space which leave the function implemented by the network intact. Two such transformations are known for feed-forward architectures: permutation of neurons within a layer, and positive scaling of all incoming weights of a neuron coupled with inverse scaling of its outgoing weights. In this work, we show for architectures with non-increasing widths that permutation and scaling are in fact the only function-preserving weight transformations. For any eligible architecture we give an explicit construction of a neural network such that any other network that implements the same function can be obtained from the original one by the application of permutations and rescaling. The proof relies on a geometric understanding of boundaries between linear regions of ReLU networks, and we hope the developed mathematical tools are of independent interest.}, author = {Bui Thi Mai, Phuong and Lampert, Christoph}, booktitle = {8th International Conference on Learning Representations}, location = {Online}, title = {{Functional vs. parametric equivalence of ReLU networks}}, year = {2020}, } @phdthesis{8390, abstract = {Deep neural networks have established a new standard for data-dependent feature extraction pipelines in the Computer Vision literature. Despite their remarkable performance in the standard supervised learning scenario, i.e. when models are trained with labeled data and tested on samples that follow a similar distribution, neural networks have been shown to struggle with more advanced generalization abilities, such as transferring knowledge across visually different domains, or generalizing to new unseen combinations of known concepts. In this thesis we argue that, in contrast to the usual black-box behavior of neural networks, leveraging more structured internal representations is a promising direction for tackling such problems. In particular, we focus on two forms of structure. First, we tackle modularity: We show that (i) compositional architectures are a natural tool for modeling reasoning tasks, in that they efficiently capture their combinatorial nature, which is key for generalizing beyond the compositions seen during training. We investigate how to to learn such models, both formally and experimentally, for the task of abstract visual reasoning. Then, we show that (ii) in some settings, modularity allows us to efficiently break down complex tasks into smaller, easier, modules, thereby improving computational efficiency; We study this behavior in the context of generative models for colorization, as well as for small objects detection. Secondly, we investigate the inherently layered structure of representations learned by neural networks, and analyze its role in the context of transfer learning and domain adaptation across visually dissimilar domains. }, author = {Royer, Amélie}, isbn = {978-3-99078-007-7}, issn = {2663-337X}, pages = {197}, publisher = {Institute of Science and Technology Austria}, title = {{Leveraging structure in Computer Vision tasks for flexible Deep Learning models}}, doi = {10.15479/AT:ISTA:8390}, year = {2020}, } @inproceedings{7937, abstract = {Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually different yet semantically close source is rarely considered: This commonly happens with real-life data, which is not necessarily as clean as the training source (noise, geometric transformations, different modalities, etc.).To tackle such scenarios, we introduce a new, generalized form of fine-tuning, called flex-tuning, in which any individual unit (e.g. layer) of a network can be tuned, and the most promising one is chosen automatically. In order to make the method appealing for practical use, we propose two lightweight and faster selection procedures that prove to be good approximations in practice. We study these selection criteria empirically across a variety of domain shifts and data scarcity scenarios, and show that fine-tuning individual units, despite its simplicity, yields very good results as an adaptation technique. As it turns out, in contrast to common practice, rather than the last fully-connected unit it is best to tune an intermediate or early one in many domain- shift scenarios, which is accurately detected by flex-tuning.}, author = {Royer, Amélie and Lampert, Christoph}, booktitle = {2020 IEEE Winter Conference on Applications of Computer Vision}, isbn = {9781728165530}, location = {Snowmass Village, CO, United States}, publisher = {IEEE}, title = {{A flexible selection scheme for minimum-effort transfer learning}}, doi = {10.1109/WACV45572.2020.9093635}, year = {2020}, } @inproceedings{7936, abstract = {State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life object detection applications, for example in remote sensing, instead require dealing with large images that contain only a few small objects of a single class, scattered heterogeneously across the space. In addition, they are often subject to strict computational constraints, such as limited battery capacity and computing power.To tackle these more practical scenarios, we propose a novel flexible detection scheme that efficiently adapts to variable object sizes and densities: We rely on a sequence of detection stages, each of which has the ability to predict groups of objects as well as individuals. Similar to a detection cascade, this multi-stage architecture spares computational effort by discarding large irrelevant regions of the image early during the detection process. The ability to group objects provides further computational and memory savings, as it allows working with lower image resolutions in early stages, where groups are more easily detected than individuals, as they are more salient. We report experimental results on two aerial image datasets, and show that the proposed method is as accurate yet computationally more efficient than standard single-shot detectors, consistently across three different backbone architectures.}, author = {Royer, Amélie and Lampert, Christoph}, booktitle = {IEEE Winter Conference on Applications of Computer Vision}, isbn = {9781728165530}, location = { Snowmass Village, CO, United States}, publisher = {IEEE}, title = {{Localizing grouped instances for efficient detection in low-resource scenarios}}, doi = {10.1109/WACV45572.2020.9093288}, year = {2020}, } @inbook{8092, abstract = {Image translation refers to the task of mapping images from a visual domain to another. Given two unpaired collections of images, we aim to learn a mapping between the corpus-level style of each collection, while preserving semantic content shared across the two domains. We introduce xgan, a dual adversarial auto-encoder, which captures a shared representation of the common domain semantic content in an unsupervised way, while jointly learning the domain-to-domain image translations in both directions. We exploit ideas from the domain adaptation literature and define a semantic consistency loss which encourages the learned embedding to preserve semantics shared across domains. We report promising qualitative results for the task of face-to-cartoon translation. The cartoon dataset we collected for this purpose, “CartoonSet”, is also publicly available as a new benchmark for semantic style transfer at https://google.github.io/cartoonset/index.html.}, author = {Royer, Amélie and Bousmalis, Konstantinos and Gouws, Stephan and Bertsch, Fred and Mosseri, Inbar and Cole, Forrester and Murphy, Kevin}, booktitle = {Domain Adaptation for Visual Understanding}, editor = {Singh, Richa and Vatsa, Mayank and Patel, Vishal M. and Ratha, Nalini}, isbn = {9783030306717}, pages = {33--49}, publisher = {Springer Nature}, title = {{XGAN: Unsupervised image-to-image translation for many-to-many mappings}}, doi = {10.1007/978-3-030-30671-7_3}, year = {2020}, } @inproceedings{6482, abstract = {Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under the specific conditions, in particular data distributions, that they were trained for. Surprisingly, none of the currently used deep network architectures have a built-in functionality that could detect if a network operates on data from a distribution it was not trained for, such that potentially a warning to the human users could be triggered. In this work, we describe KS(conf), a procedure for detecting such outside of specifications (out-of-specs) operation, based on statistical testing of the network outputs. We show by extensive experiments using the ImageNet, AwA2 and DAVIS datasets on a variety of ConvNets architectures that KS(conf) reliably detects out-of-specs situations. It furthermore has a number of properties that make it a promising candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with all networks, including pretrained ones, and requires no a priori knowledge of how the data distribution could change. }, author = {Sun, Rémy and Lampert, Christoph}, isbn = {9783030129385}, issn = {1611-3349}, location = {Stuttgart, Germany}, pages = {244--259}, publisher = {Springer Nature}, title = {{KS(conf): A light-weight test if a ConvNet operates outside of Its specifications}}, doi = {10.1007/978-3-030-12939-2_18}, volume = {11269}, year = {2019}, } @article{6554, abstract = {Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits of publicly available datasets used for this task. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Moreover, we propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2) dataset which we make publicly available both in terms of image features and the images themselves. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss in detail the limitations of the current status of the area which can be taken as a basis for advancing it.}, author = {Xian, Yongqin and Lampert, Christoph and Schiele, Bernt and Akata, Zeynep}, issn = {1939-3539}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {9}, pages = {2251 -- 2265}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly}}, doi = {10.1109/tpami.2018.2857768}, volume = {41}, year = {2019}, } @inproceedings{6569, abstract = {Knowledge distillation, i.e. one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much faster and more reliably if trained with the outputs of another classifier as soft labels, instead of from ground truth data. So far, however, there is no satisfactory theoretical explanation of this phenomenon. In this work, we provide the first insights into the working mechanisms of distillation by studying the special case of linear and deep linear classifiers. Specifically, we prove a generalization bound that establishes fast convergence of the expected risk of a distillation-trained linear classifier. From the bound and its proof we extract three keyfactors that determine the success of distillation: data geometry – geometric properties of the datadistribution, in particular class separation, has an immediate influence on the convergence speed of the risk; optimization bias– gradient descentoptimization finds a very favorable minimum of the distillation objective; and strong monotonicity– the expected risk of the student classifier always decreases when the size of the training set grows.}, author = {Bui Thi Mai, Phuong and Lampert, Christoph}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, location = {Long Beach, CA, United States}, pages = {5142--5151}, publisher = {ML Research Press}, title = {{Towards understanding knowledge distillation}}, volume = {97}, year = {2019}, } @inproceedings{6942, abstract = {Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of 𝜔 -regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees.}, author = {Ashok, Pranav and Brázdil, Tomáš and Chatterjee, Krishnendu and Křetínský, Jan and Lampert, Christoph and Toman, Viktor}, booktitle = {16th International Conference on Quantitative Evaluation of Systems}, isbn = {9783030302801}, issn = {0302-9743}, location = {Glasgow, United Kingdom}, pages = {109--128}, publisher = {Springer Nature}, title = {{Strategy representation by decision trees with linear classifiers}}, doi = {10.1007/978-3-030-30281-8_7}, volume = {11785}, year = {2019}, } @book{7171, abstract = {Wissen Sie, was sich hinter künstlicher Intelligenz und maschinellem Lernen verbirgt? Dieses Sachbuch erklärt Ihnen leicht verständlich und ohne komplizierte Formeln die grundlegenden Methoden und Vorgehensweisen des maschinellen Lernens. Mathematisches Vorwissen ist dafür nicht nötig. Kurzweilig und informativ illustriert Lisa, die Protagonistin des Buches, diese anhand von Alltagssituationen. Ein Buch für alle, die in Diskussionen über Chancen und Risiken der aktuellen Entwicklung der künstlichen Intelligenz und des maschinellen Lernens mit Faktenwissen punkten möchten. Auch für Schülerinnen und Schüler geeignet!}, editor = {Kersting, Kristian and Lampert, Christoph and Rothkopf, Constantin}, isbn = {978-3-658-26762-9}, pages = {XIV, 245}, publisher = {Springer Nature}, title = {{Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt}}, doi = {10.1007/978-3-658-26763-6}, year = {2019}, } @inproceedings{7640, abstract = {We propose a new model for detecting visual relationships, such as "person riding motorcycle" or "bottle on table". This task is an important step towards comprehensive structured mage understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on two datasets, V-COCO and Open Images, demonstrating strong quantitative and qualitative results.}, author = {Kolesnikov, Alexander and Kuznetsova, Alina and Lampert, Christoph and Ferrari, Vittorio}, booktitle = {Proceedings of the 2019 International Conference on Computer Vision Workshop}, isbn = {9781728150239}, location = {Seoul, South Korea}, publisher = {IEEE}, title = {{Detecting visual relationships using box attention}}, doi = {10.1109/ICCVW.2019.00217}, year = {2019}, } @inproceedings{6590, abstract = {Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality of these sources is not always guaranteed. As additional complications, the data might be stored in a distributed way, or might even have to remain private. In this work, we address the question of how to learn robustly in such scenarios. Studying the problem through the lens of statistical learning theory, we derive a procedure that allows for learning from all available sources, yet automatically suppresses irrelevant or corrupted data. We show by extensive experiments that our method provides significant improvements over alternative approaches from robust statistics and distributed optimization. }, author = {Konstantinov, Nikola H and Lampert, Christoph}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, location = {Long Beach, CA, USA}, pages = {3488--3498}, publisher = {ML Research Press}, title = {{Robust learning from untrusted sources}}, volume = {97}, year = {2019}, }