@misc{23036,
  author       = {Valentini, Marco},
  publisher    = {Zenodo},
  title        = {{Data repository for 'Parity-conserving Cooper-pair transport and ideal superconducting diode in planar Germanium'}},
  doi          = {10.5281/zenodo.10119345},
  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},
}

@inproceedings{14458,
  abstract     = {We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models. We can execute SparseGPT on the largest available open-source models, OPT-175B and BLOOM-176B, in under 4.5 hours, and can reach 60% unstructured sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these models can be ignored at inference time. SparseGPT generalizes to semi-structured (2:4 and 4:8) patterns, and is compatible with weight quantization approaches. The code is available at: https://github.com/IST-DASLab/sparsegpt.},
  author       = {Frantar, Elias and Alistarh, Dan-Adrian},
  booktitle    = {Proceedings of the 40th International Conference on Machine Learning},
  issn         = {2640-3498},
  location     = {Honolulu, Hawaii, HI, United States},
  pages        = {10323--10337},
  publisher    = {ML Research Press},
  title        = {{SparseGPT: Massive language models can be accurately pruned in one-shot}},
  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{12334,
  abstract     = {Regulation of the Arp2/3 complex is required for productive nucleation of branched actin networks. An emerging aspect of regulation is the incorporation of subunit isoforms into the Arp2/3 complex. Specifically, both ArpC5 subunit isoforms, ArpC5 and ArpC5L, have been reported to fine-tune nucleation activity and branch junction stability. We have combined reverse genetics and cellular structural biology to describe how ArpC5 and ArpC5L differentially affect cell migration. Both define the structural stability of ArpC1 in branch junctions and, in turn, by determining protrusion characteristics, affect protein dynamics and actin network ultrastructure. ArpC5 isoforms also affect the positioning of members of the Ena/Vasodilator-stimulated phosphoprotein (VASP) family of actin filament elongators, which mediate ArpC5 isoform–specific effects on the actin assembly level. Our results suggest that ArpC5 and Ena/VASP proteins are part of a signaling pathway enhancing cell migration.</jats:p>},
  author       = {Fäßler, Florian and Javoor, Manjunath and Datler, Julia and Döring, Hermann and Hofer, Florian and Dimchev, Georgi A and Hodirnau, Victor-Valentin and Faix, Jan and Rottner, Klemens and Schur, Florian KM},
  issn         = {2375-2548},
  journal      = {Science Advances},
  keywords     = {Multidisciplinary},
  number       = {3},
  publisher    = {American Association for the Advancement of Science},
  title        = {{ArpC5 isoforms regulate Arp2/3 complex–dependent protrusion through differential Ena/VASP positioning}},
  doi          = {10.1126/sciadv.add6495},
  volume       = {9},
  year         = {2023},
}

@unpublished{17351,
  abstract     = {Contractive coupling rates have been recently introduced by Conforti as a
tool to establish convex Sobolev inequalities (including modified log-Sobolev
and Poincar\'{e} inequality) for some classes of Markov chains. In this work,
we show how contractive coupling rates can also be used to prove stronger
inequalities, in the form of curvature lower bounds for Markov chains and
geodesic convexity of entropic functionals. We illustrate this in several
examples discussed by Conforti, where in particular, after appropriately
choosing a parameter function, we establish positive curvature in the entropic
and (discrete) Bakry--\'{E}mery sense. In addition, we recall and give
straightforward generalizations of some notions of coarse Ricci curvature, and
we discuss some of their properties and relations with the concepts of
couplings and coupling rates: as an application, we show exponential
contraction of the $p$-Wasserstein distance for the heat flow in the
aforementioned examples.},
  author       = {Pedrotti, Francesco},
  booktitle    = {arXiv},
  title        = {{Contractive coupling rates and curvature lower bounds for Markov chains}},
  doi          = {10.48550/arXiv.2308.00516},
  year         = {2023},
}

@article{13267,
  abstract     = {Three-dimensional (3D) reconstruction of living brain tissue down to an individual synapse level would create opportunities for decoding the dynamics and structure–function relationships of the brain’s complex and dense information processing network; however, this has been hindered by insufficient 3D resolution, inadequate signal-to-noise ratio and prohibitive light burden in optical imaging, whereas electron microscopy is inherently static. Here we solved these challenges by developing an integrated optical/machine-learning technology, LIONESS (live information-optimized nanoscopy enabling saturated segmentation). This leverages optical modifications to stimulated emission depletion microscopy in comprehensively, extracellularly labeled tissue and previous information on sample structure via machine learning to simultaneously achieve isotropic super-resolution, high signal-to-noise ratio and compatibility with living tissue. This allows dense deep-learning-based instance segmentation and 3D reconstruction at a synapse level, incorporating molecular, activity and morphodynamic information. LIONESS opens up avenues for studying the dynamic functional (nano-)architecture of living brain tissue.},
  author       = {Velicky, Philipp and Miguel Villalba, Eder and Michalska, Julia M and Lyudchik, Julia and Wei, Donglai and Lin, Zudi and Watson, Jake and Troidl, Jakob and Beyer, Johanna and Ben Simon, Yoav and Sommer, Christoph M and Jahr, Wiebke and Cenameri, Alban and Broichhagen, Johannes and Grant, Seth G.N. and Jonas, Peter M and Novarino, Gaia and Pfister, Hanspeter and Bickel, Bernd and Danzl, Johann G},
  issn         = {1548-7105},
  journal      = {Nature Methods},
  pages        = {1256--1265},
  publisher    = {Springer Nature},
  title        = {{Dense 4D nanoscale reconstruction of living brain tissue}},
  doi          = {10.1038/s41592-023-01936-6},
  volume       = {20},
  year         = {2023},
}

@article{13227,
  abstract     = {Currently available quantum processors are dominated by noise, which severely limits their applicability and motivates the search for new physical qubit encodings. In this work, we introduce the inductively shunted transmon, a weakly flux-tunable superconducting qubit that offers charge offset protection for all levels and a 20-fold reduction in flux dispersion compared to the state-of-the-art resulting in a constant coherence over a full flux quantum. The parabolic confinement provided by the inductive shunt as well as the linearity of the geometric superinductor facilitates a high-power readout that resolves quantum jumps with a fidelity and QND-ness of >90% and without the need for a Josephson parametric amplifier. Moreover, the device reveals quantum tunneling physics between the two prepared fluxon ground states with a measured average decay time of up to 3.5 h. In the future, fast time-domain control of the transition matrix elements could offer a new path forward to also achieve full qubit control in the decay-protected fluxon basis.},
  author       = {Hassani, Farid and Peruzzo, Matilda and Kapoor, Lucky and Trioni, Andrea and Zemlicka, Martin and Fink, Johannes M},
  issn         = {2041-1723},
  journal      = {Nature Communications},
  publisher    = {Springer Nature},
  title        = {{Inductively shunted transmons exhibit noise insensitive plasmon states and a fluxon decay exceeding 3 hours}},
  doi          = {10.1038/s41467-023-39656-2},
  volume       = {14},
  year         = {2023},
}

@unpublished{18294,
  abstract     = {Using a two-dimensional version of the delta method, we establish an asymptotic formula for the number of rational points of bounded height on non-singular complete intersections of cubic and quadric hypersurfaces of dimension at least 23 over Fq(t), provided cha(Fq)>3. Under the same hypotheses, we also verify weak approximation.},
  author       = {Glas, Jakob},
  booktitle    = {arXiv},
  title        = {{Complete intersections of cubic and quadric hypersurfaces over Fq(t)}},
  doi          = {10.48550/arXiv.2306.02718},
  year         = {2023},
}

@misc{23142,
  abstract     = {It contains the benchmarks and the results of comparison between STORM, PET and MultiGain for the QComp category of Long-Run Average rewards.},
  author       = {Grover, Kush and Weiniger, Maximilian and Kretinsky, Jan},
  publisher    = {Zenodo},
  title        = {{QComp LRA results}},
  doi          = {10.5281/zenodo.8219190},
  year         = {2023},
}

@inproceedings{14417,
  abstract     = {Entropic risk (ERisk) is an established risk measure in finance, quantifying risk by an exponential re-weighting of rewards. We study ERisk for the first time in the context of turn-based stochastic games with the total reward objective. This gives rise to an objective function that demands the control of systems in a risk-averse manner. We show that the resulting games are determined and, in particular, admit optimal memoryless deterministic strategies. This contrasts risk measures that previously have been considered in the special case of Markov decision processes and that require randomization and/or memory. We provide several results on the decidability and the computational complexity of the threshold problem, i.e. whether the optimal value of ERisk exceeds a given threshold. In the most general case, the problem is decidable subject to Shanuel’s conjecture. If all inputs are rational, the resulting threshold problem can be solved using algebraic numbers, leading to decidability via a polynomial-time reduction to the existential theory of the reals. Further restrictions on the encoding of the input allow the solution of the threshold problem in NP∩coNP. Finally, an approximation algorithm for the optimal value of ERisk is provided.},
  author       = {Baier, Christel and Chatterjee, Krishnendu and Meggendorfer, Tobias and Piribauer, Jakob},
  booktitle    = {48th International Symposium on Mathematical Foundations of Computer Science},
  isbn         = {9783959772921},
  issn         = {1868-8969},
  location     = {Bordeaux, France},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
  title        = {{Entropic risk for turn-based stochastic games}},
  doi          = {10.4230/LIPIcs.MFCS.2023.15},
  volume       = {272},
  year         = {2023},
}

@inproceedings{19985,
  abstract     = {We consider a natural problem dealing with weighted packet selection across a rechargeable link, which e.g., finds applications in cryptocurrency networks. The capacity of a link (u, v) is determined by how much nodes u and v allocate for this link. Specifically, the input is a finite ordered sequence of packets that arrive in both directions along a link. Given (u, v) and a packet of weight x going from u to v, node u can either accept or reject the packet. If u accepts the packet, the capacity on link (u, v) decreases by x. Correspondingly, v’s capacity on (u, v) increases by x. If a node rejects the packet, this will entail a cost affinely linear in the weight of the packet. A link is “rechargeable” in the sense that the total capacity of the link has to remain constant, but the allocation of capacity at the ends of the link can depend arbitrarily on the nodes’ decisions. The goal is to minimise the sum of the capacity injected into the link and the cost of rejecting packets. We show that the problem is NP-hard, but can be approximated efficiently with a ratio of (1 + E) . (1 + square3) for some arbitrary E>0.},
  author       = {Schmid, Stefan and Svoboda, Jakub and Yeo, Michelle X},
  booktitle    = {30th International Colloquium on Structural Information and Communication Complexity},
  isbn         = {9783031327322},
  issn         = {1611-3349},
  location     = {Alcalá de Henares, Spain},
  pages        = {576--594},
  publisher    = {Springer Nature},
  title        = {{Weighted acket selection for rechargeable links in cryptocurrency networks: Complexity and approximation}},
  doi          = {10.1007/978-3-031-32733-9_26},
  volume       = {13892},
  year         = {2023},
}

@unpublished{17173,
  abstract     = {Consider the random variable $\mathrm{Tr}( f_1(W)A_1\dots f_k(W)A_k)$ where $W$ is an $N\times N$ Hermitian Wigner matrix, $k\in\mathbb{N}$, and choose (possibly $N$-dependent) regular functions $f_1,\dots, f_k$ as well as bounded deterministic matrices $A_1,\dots,A_k$. We give a functional central limit theorem showing that the fluctuations around the expectation are Gaussian. Moreover, we determine the limiting covariance structure and give explicit error bounds in terms of the scaling of $f_1,\dots,f_k$ and the number of traceless matrices among $A_1,\dots,A_k$, thus extending the results of [Cipolloni, Erdős, Schröder 2023] to products of arbitrary length $k\geq2$. As an application, we consider the fluctuation of $\mathrm{Tr}(\mathrm{e}^{\mathrm{i} tW}A_1\mathrm{e}^{-\mathrm{i} tW}A_2)$ around its thermal value $\mathrm{Tr}(A_1)\mathrm{Tr}(A_2)$ when $t$ is large and give an explicit formula for the variance.},
  author       = {Reker, Jana},
  booktitle    = {arXiv},
  title        = {{Multi-point functional central limit theorem for Wigner Matrices}},
  doi          = {10.48550/arXiv.2307.11028},
  year         = {2023},
}

@unpublished{17174,
  abstract     = {We prove that a class of weakly perturbed Hamiltonians of the form $H_λ= H_0 + λW$, with $W$ being a Wigner matrix, exhibits prethermalization. That is, the time evolution generated by $H_λ$ relaxes to its ultimate thermal state via an intermediate prethermal state with a lifetime of order $λ^{-2}$. Moreover, we obtain a general relaxation formula, expressing the perturbed dynamics via the unperturbed dynamics and the ultimate thermal state. The proof relies on a two-resolvent law for the deformed Wigner matrix $H_λ$.},
  author       = {Erdös, László and Henheik, Sven Joscha and Reker, Jana and Riabov, Volodymyr},
  booktitle    = {arXiv},
  title        = {{Prethermalization for deformed Wigner Matrices}},
  doi          = {10.48550/arXiv.2310.06677},
  year         = {2023},
}

@inproceedings{14922,
  abstract     = {We propose a novel approach to concentration for non-independent random variables. The main idea is to ``pretend'' that the random variables are independent and pay a multiplicative price measuring how far they are from actually being independent. This price is encapsulated in the Hellinger integral between the joint and the product of the marginals, which is then upper bounded leveraging tensorisation properties. Our bounds represent a natural generalisation of concentration inequalities in the presence of dependence: we recover exactly the classical bounds (McDiarmid's inequality) when the random variables are independent. Furthermore, in a ``large deviations'' regime, we obtain the same decay in the probability as for the independent case, even when the random variables display non-trivial dependencies. To show this, we consider a number of applications of interest. First, we provide a bound for Markov chains with finite state space. Then, we consider the Simple Symmetric Random Walk, which is a non-contracting Markov chain, and a non-Markovian setting in which the stochastic process depends on its entire past. To conclude, we propose an application to Markov Chain Monte Carlo methods, where our approach leads to an improved lower bound on the minimum burn-in period required to reach a certain accuracy. In all of these settings, we provide a regime of parameters in which our bound fares better than what the state of the art can provide.},
  author       = {Esposito, Amedeo Roberto and Mondelli, Marco},
  booktitle    = {Proceedings of 2023 IEEE International Symposium on Information Theory},
  issn         = {2157-8117},
  location     = {Taipei, Taiwan},
  pages        = {400--405},
  publisher    = {IEEE},
  title        = {{Concentration without independence via information measures}},
  doi          = {10.1109/isit54713.2023.10206899},
  year         = {2023},
}

@inproceedings{14083,
  abstract     = {In this work we consider the list-decodability and list-recoverability of arbitrary q-ary codes, for all integer values of q ≥ 2. A code is called (p,L)_q-list-decodable if every radius pn Hamming ball contains less than L codewords; (p,𝓁,L)_q-list-recoverability is a generalization where we place radius pn Hamming balls on every point of a combinatorial rectangle with side length 𝓁 and again stipulate that there be less than L codewords.
Our main contribution is to precisely calculate the maximum value of p for which there exist infinite families of positive rate (p,𝓁,L)_q-list-recoverable codes, the quantity we call the zero-rate threshold. Denoting this value by p_*, we in fact show that codes correcting a p_*+ε fraction of errors must have size O_ε(1), i.e., independent of n. Such a result is typically referred to as a "Plotkin bound." To complement this, a standard random code with expurgation construction shows that there exist positive rate codes correcting a p_*-ε fraction of errors. We also follow a classical proof template (typically attributed to Elias and Bassalygo) to derive from the zero-rate threshold other tradeoffs between rate and decoding radius for list-decoding and list-recovery.
Technically, proving the Plotkin bound boils down to demonstrating the Schur convexity of a certain function defined on the q-simplex as well as the convexity of a univariate function derived from it. We remark that an earlier argument claimed similar results for q-ary list-decoding; however, we point out that this earlier proof is flawed.},
  author       = {Resch, Nicolas and Yuan, Chen and Zhang, Yihan},
  booktitle    = {50th International Colloquium on Automata, Languages, and Programming},
  isbn         = {9783959772785},
  issn         = {1868-8969},
  location     = {Paderborn, Germany},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
  title        = {{Zero-rate thresholds and new capacity bounds for list-decoding and list-recovery}},
  doi          = {10.4230/LIPIcs.ICALP.2023.99},
  volume       = {261},
  year         = {2023},
}

@article{13276,
  abstract     = {We introduce a generic and accessible implementation of an exact diagonalization method for studying few-fermion models. Our aim is to provide a testbed for the newcomers to the field as well as a stepping stone for trying out novel optimizations and approximations. This userguide consists of a description of the algorithm, and several examples in varying orders of sophistication. In particular, we exemplify our routine using an effective-interaction approach that fixes the low-energy physics. We benchmark this approach against the existing data, and show that it is able to deliver state-of-the-art numerical results at a significantly reduced computational cost.},
  author       = {Rammelmüller, Lukas and Huber, David and Volosniev, Artem},
  issn         = {2949-804X},
  journal      = {SciPost Physics Codebases},
  publisher    = {SciPost Foundation},
  title        = {{A modular implementation of an effective interaction approach for harmonically trapped fermions in 1D}},
  doi          = {10.21468/scipostphyscodeb.12},
  year         = {2023},
}

@misc{13275,
  abstract     = {We introduce a generic and accessible implementation of an exact diagonalization method for studying few-fermion models. Our aim is to provide a testbed for the newcomers to the field as well as a stepping stone for trying out novel optimizations and approximations. This userguide consists of a description of the algorithm, and several examples in varying orders of sophistication. In particular, we exemplify our routine using an effective-interaction approach that fixes the low-energy physics. We benchmark this approach against the existing data, and show that it is able to deliver state-of-the-art numerical results at a significantly reduced computational cost.},
  author       = {Rammelmüller, Lukas and Huber, David and Volosniev, Artem},
  publisher    = {SciPost Foundation},
  title        = {{Codebase release 1.0 for FermiFCI}},
  doi          = {10.21468/scipostphyscodeb.12-r1.0},
  year         = {2023},
}

@inproceedings{13236,
  abstract     = {We present an auction algorithm using multiplicative instead of constant weight updates to compute a (1−ε)-approximate maximum weight matching (MWM) in a bipartite graph with n vertices and m edges in time O(mε−1log(ε−1)), matching the running time of the linear-time approximation algorithm of Duan and Pettie [JACM ’14]. Our algorithm is very simple and it can be extended to give a dynamic data structure that maintains a (1−ε)-approximate maximum weight matching under (1) one-sided vertex deletions (with incident edges) and (2) one-sided vertex insertions (with incident edges sorted by weight) to the other side. The total time time used is O(mε−1log(ε−1)), where m is the sum of the number of initially existing and inserted edges.},
  author       = {Zheng, Da Wei and Henzinger, Monika H},
  booktitle    = {International Conference on Integer Programming and Combinatorial Optimization},
  isbn         = {9783031327254},
  issn         = {1611-3349},
  location     = {Madison, WI, United States},
  pages        = {453--465},
  publisher    = {Springer Nature},
  title        = {{Multiplicative auction algorithm for approximate maximum weight bipartite matching}},
  doi          = {10.1007/978-3-031-32726-1_32},
  volume       = {13904},
  year         = {2023},
}

@misc{22867,
  abstract     = {The impact of ongoing climate change on populations will be contingent upon their contemporary adaptive evolution. In this study, we investigated the contemporary evolution of four populations of the cold-water kelp Laminaria digitata by analysing their spatial and temporal genomic variation using ddRAD-sequencing. These populations were sampled from the center to the southern margin of its north-eastern Atlantic distribution at two-time points, spanning at least two generations. Through genome scans for local adaptation at a single time point, we identified candidate loci that showed clinal variation correlated with changes in sea surface temperature (SST) along latitudinal gradients. This finding suggests that SST may drive the adaptive response of these kelp populations, although factors such as species' demographic history should also be considered. Additionally, we performed a simulation approach to distinguish the effect of selection from genetic drift in allele frequency changes over time. This enabled the detection of loci in the southernmost population that exhibited temporal differentiation beyond what would be expected from genetic drift alone: these are candidate loci which could have evolved under selection over time. In contrast, we did not detect any outlier locus based on temporal differentiation in the population from the North Sea, which also displayed low and decreasing levels of genetic diversity. The diverse evolutionary scenarios observed among populations can be attributed to variations in the prevalence of selection relative to genetic drift across different environments. Therefore, our study highlights the potential of temporal genomics to offer valuable insights into the contemporary evolution of marine foundation species facing climate change.},
  author       = {Reynes, Lauric},
  publisher    = {Repository},
  title        = {{Genomic datasets of Laminaria digitata: Paired-end reads from dd-RADseq, reference genome assembly and filtered VCF}},
  doi          = {10.5061/dryad.tb2rbp064},
  year         = {2023},
}

