@article{14849, abstract = {We establish a precise three-term asymptotic expansion, with an optimal estimate of the error term, for the rightmost eigenvalue of an n×n random matrix with independent identically distributed complex entries as n tends to infinity. All terms in the expansion are universal.}, author = {Cipolloni, Giorgio and Erdös, László and Schröder, Dominik J and Xu, Yuanyuan}, issn = {0091-1798}, journal = {The Annals of Probability}, keywords = {Statistics, Probability and Uncertainty, Statistics and Probability}, number = {6}, pages = {2192--2242}, publisher = {Institute of Mathematical Statistics}, title = {{On the rightmost eigenvalue of non-Hermitian random matrices}}, doi = {10.1214/23-aop1643}, volume = {51}, year = {2023}, } @inbook{14853, abstract = {Organization – or departure from a random pattern – in tropical deep convection is heavily studied due to its immediate relevance to climate sensitivity and extremes. Low-latitude convection has motivated numerical model idealizations, where the Coriolis force is removed and boundary conditions are simplified spatially and temporally. One of the most stunning aspects of such idealized simulated cloud organization is the spontaneous clumping of convection that can occur without any predetermining external perturbation, such as inhomogeneous surface boundary conditions or large-scale waves. Whereas individual convective rain cells measure only few kilometers in horizontal diameter, the clusters they form can often span hundreds or even thousands of kilometers. Hence, organization may emerge from the very small scales but can show effects at the synoptic scale. We refer to such emergent organization as convective self-organization. Convective self-organization thus features characteristics of emergence, such as non-trivial system-scale pattern formation or hysteresis. We summarize observational evidence for large-scale organization and briefly recap classical idealized modeling studies that yield convective self-aggregation – emergent organization under strongly idealized boundary conditions. We then focus on developing research, where temporal variation, such as the diurnal cycle, or two-way interactive surface properties yield distinct organizational modes. Convectively generated cold pools and mesoscale convective systems, both ubiquitous in nature, are thereby found to potentially play key roles in promoting – rather than suppressing – sustained system-scale organization.}, author = {Haerter, Jan O. and Muller, Caroline J}, booktitle = {Clouds and Their Climatic Impacts}, editor = {Sullivan, Sylvia and Hoose, Corinna}, isbn = {9781119700319}, issn = {2328-8779}, pages = {179--193}, publisher = {Wiley}, title = {{Mechanisms for the Self‐Organization of Tropical Deep Convection}}, doi = {10.1002/9781119700357.ch8}, year = {2023}, } @article{14854, abstract = {We study the spectrum of the Fröhlich Hamiltonian for the polaron at fixed total momentum. We prove the existence of excited eigenvalues between the ground state energy and the essential spectrum at strong coupling. In fact, our main result shows that the number of excited energy bands diverges in the strong coupling limit. To prove this we derive upper bounds for the min-max values of the corresponding fiber Hamiltonians and compare them with the bottom of the essential spectrum, a lower bound on which was recently obtained by Brooks and Seiringer (Comm. Math. Phys. 404:1 (2023), 287–337). The upper bounds are given in terms of the ground state energy band shifted by momentum-independent excitation energies determined by an effective Hamiltonian of Bogoliubov type.}, author = {Mitrouskas, David Johannes and Seiringer, Robert}, issn = {2578-5885}, journal = {Pure and Applied Analysis}, keywords = {General Medicine}, number = {4}, pages = {973--1008}, publisher = {Mathematical Sciences Publishers}, title = {{Ubiquity of bound states for the strongly coupled polaron}}, doi = {10.2140/paa.2023.5.973}, volume = {5}, year = {2023}, } @misc{14861, abstract = {Cover Page}, author = {Becker, Lea Marie and Berbon, Mélanie and Vallet, Alicia and Grelard, Axelle and Morvan, Estelle and Bardiaux, Benjamin and Lichtenecker, Roman and Ernst, Matthias and Loquet, Antoine and Schanda, Paul}, booktitle = {Angewandte Chemie International Edition}, issn = {1521-3773}, keywords = {General Chemistry, Catalysis}, number = {19}, publisher = {Wiley}, title = {{Cover Picture: The rigid core and flexible surface of amyloid fibrils probed by Magic‐Angle‐Spinning NMR spectroscopy of aromatic residues}}, doi = {10.1002/anie.202304138}, volume = {62}, year = {2023}, } @inproceedings{14864, author = {Stöllner, Andrea and Lenton, Isaac C and Muller, Caroline J and Waitukaitis, Scott R}, booktitle = {EGU General Assembly 2023}, location = {Vienna, Austria & Virtual}, publisher = {European Geosciences Union}, title = {{Measuring spontaneous charging of single aerosol particles}}, doi = {10.5194/egusphere-egu23-6166}, year = {2023}, } @inproceedings{14865, author = {Hwong, Yi-Ling and Colin, Maxime and Aglas, Philipp and Muller, Caroline J and Sherwood, Steven}, booktitle = {EGU General Assembly 2023}, location = {Vienna, Austria & Virtual}, publisher = {European Geosciences Union}, title = {{Evaluating memory properties in convection schemes using idealised tests}}, doi = {10.5194/egusphere-egu23-4968}, year = {2023}, } @inproceedings{14866, author = {Abramian, Sophie and Muller, Caroline J and Risi, Camille}, booktitle = {EGU General Assembly 2023}, location = {Vienna, Austria & Virtual}, publisher = {European Geosciences Union}, title = {{Extreme precipitation in tropical squall lines}}, doi = {10.5194/egusphere-egu23-15870}, year = {2023}, } @inproceedings{14867, abstract = {Starting with the empty graph on $[n]$, at each round, a set of $K=K(n)$ edges is presented chosen uniformly at random from the ones that have not been presented yet. We are then asked to choose at most one of the presented edges and add it to the current graph. Our goal is to construct a Hamiltonian graph with $(1+o(1))n$ edges within as few rounds as possible. We show that in this process, one can build a Hamiltonian graph of size $(1+o(1))n$ in $(1+o(1))(1+(\log n)/2K) n$ rounds w.h.p. The case $K=1$ implies that w.h.p. one can build a Hamiltonian graph by choosing $(1+o(1))n$ edges in an online fashion as they appear along the first $(0.5+o(1))n\log n$ rounds of the random graph process. This answers a question of Frieze, Krivelevich and Michaeli. Observe that the number of rounds is asymptotically optimal as the first $0.5n\log n$ edges do not span a Hamilton cycle w.h.p. The case $K=\Theta(\log n)$ implies that the Hamiltonicity threshold of the corresponding Achlioptas process is at most $(1+o(1))(1+(\log n)/2K) n$. This matches the $(1-o(1))(1+(\log n)/2K) n$ lower bound due to Krivelevich, Lubetzky and Sudakov and resolves the problem of determining the Hamiltonicity threshold of the Achlioptas process with $K=\Theta(\log n)$. We also show that in the above process one can construct a graph $G$ that spans a matching of size $\lfloor V(G)/2) \rfloor$ and $(0.5+o(1))n$ edges within $(1+o(1))(0.5+(\log n)/2K) n$ rounds w.h.p. Our proof relies on a robust Hamiltonicity property of the strong $4$-core of the binomial random graph which we use as a black-box. This property allows it to absorb paths covering vertices outside the strong $4$-core into a cycle.}, author = {Anastos, Michael}, booktitle = {Proceedings of the 12th European Conference on Combinatorics, Graph Theory and Applications}, issn = {2788-3116}, location = {Prague, Czech Republic}, pages = {36--41}, publisher = {Masaryk University Press}, title = {{Constructing Hamilton cycles and perfect matchings efficiently}}, doi = {10.5817/cz.muni.eurocomb23-005}, year = {2023}, } @article{14868, abstract = {The role of nuclear pore complexes (NPCs) in genome organization remains poorly characterized due to technical limitations in probing genome-wide protein-DNA interactions specific to the nuclear periphery. Here, we developed a new sensitive method, NPC-DamID, which combines in vitro reconstitution of nuclear import and DamID technology. The fixation-free method identifies chromatin interactions at the NPCs in intact nuclei from cells and tissues. We found that NPCs are preferentially associated with common and hierarchically arranged super-enhancers (SEs) across multiple cell types. We also uncovered phase-separated condensates at NPCs that compartmentalize and concentrate transcriptional coactivators and structural proteins at SE-regulated genes. Our results support NPCs as anchoring sites for SE regulatory hubs and cell-type-specific transcriptional control.}, author = {Tyagi, Swati and Capitanio, Juliana S. and Xu, Jiawei and Chen, Fei and Sharma, Rahul and Huang, Jialiang and HETZER, Martin W}, journal = {eLife}, publisher = {eLife Sciences Publications}, title = {{High-precision mapping of nuclear pore-chromatin interactions reveals new principles of genome organization at the nuclear envelope}}, doi = {10.7554/elife.87462}, year = {2023}, } @inproceedings{14872, abstract = {We entangled microwave and optical photons for the first time as verified by a measured two-mode vacuum squeezing of 0.7 dB. This electro-optic entanglement is the key resource needed to connect cryogenic quantum circuits.}, author = {Sahu, Rishabh and Qiu, Liu and Hease, William J and Arnold, Georg M and Minoguchi, Yuri and Rabl, Peter and Fink, Johannes M}, booktitle = {Frontiers in Optics + Laser Science 2023}, isbn = {9781957171296}, location = {Tacoma, WA, United States}, publisher = {Optica Publishing Group}, title = {{Entangling microwaves and telecom wavelength light}}, doi = {10.1364/ls.2023.lm1f.3}, year = {2023}, } @article{14920, abstract = {We consider fixpoint algorithms for two-player games on graphs with $\omega$-regular winning conditions, where the environment is constrained by a strong transition fairness assumption. Strong transition fairness is a widely occurring special case of strong fairness, which requires that any execution is strongly fair with respect to a specified set of live edges: whenever the source vertex of a live edge is visited infinitely often along a play, the edge itself is traversed infinitely often along the play as well. We show that, surprisingly, strong transition fairness retains the algorithmic characteristics of the fixpoint algorithms for $\omega$-regular games -- the new algorithms have the same alternation depth as the classical algorithms but invoke a new type of predecessor operator. For Rabin games with $k$ pairs, the complexity of the new algorithm is $O(n^{k+2}k!)$ symbolic steps, which is independent of the number of live edges in the strong transition fairness assumption. Further, we show that GR(1) specifications with strong transition fairness assumptions can be solved with a 3-nested fixpoint algorithm, same as the usual algorithm. In contrast, strong fairness necessarily requires increasing the alternation depth depending on the number of fairness assumptions. We get symbolic algorithms for (generalized) Rabin, parity and GR(1) objectives under strong transition fairness assumptions as well as a direct symbolic algorithm for qualitative winning in stochastic $\omega$-regular games that runs in $O(n^{k+2}k!)$ symbolic steps, improving the state of the art. Finally, we have implemented a BDD-based synthesis engine based on our algorithm. We show on a set of synthetic and real benchmarks that our algorithm is scalable, parallelizable, and outperforms previous algorithms by orders of magnitude.}, author = {Banerjee, Tamajit and Majumdar, Rupak and Mallik, Kaushik and Schmuck, Anne-Kathrin and Soudjani, Sadegh}, issn = {2751-4838}, journal = {TheoretiCS}, publisher = {EPI Sciences}, title = {{Fast symbolic algorithms for mega-regular games under strong transition fairness}}, doi = {10.46298/theoretics.23.4}, volume = {2}, year = {2023}, } @inproceedings{14923, abstract = {We study the performance of a Bayesian statistician who estimates a rank-one signal corrupted by non-symmetric rotationally invariant noise with a generic distribution of singular values. As the signal-to-noise ratio and the noise structure are unknown, a Gaussian setup is incorrectly assumed. We derive the exact analytic expression for the error of the mismatched Bayes estimator and also provide the analysis of an approximate message passing (AMP) algorithm. The first result exploits the asymptotic behavior of spherical integrals for rectangular matrices and of low-rank matrix perturbations; the second one relies on the design and analysis of an auxiliary AMP. The numerical experiments show that there is a performance gap between the AMP and Bayes estimators, which is due to the incorrect estimation of the signal norm.}, author = {Fu, Teng and Liu, YuHao and Barbier, Jean and Mondelli, Marco and Liang, ShanSuo and Hou, TianQi}, booktitle = {Proceedings of 2023 IEEE International Symposium on Information Theory}, isbn = {9781665475549}, issn = {2157-8117}, location = {Taipei, Taiwan}, pages = {1178--1183}, publisher = {IEEE}, title = {{Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise}}, doi = {10.1109/isit54713.2023.10206671}, year = {2023}, } @inproceedings{14924, abstract = {The stochastic heavy ball method (SHB), also known as stochastic gradient descent (SGD) with Polyak's momentum, is widely used in training neural networks. However, despite the remarkable success of such algorithm in practice, its theoretical characterization remains limited. In this paper, we focus on neural networks with two and three layers and provide a rigorous understanding of the properties of the solutions found by SHB: \emph{(i)} stability after dropping out part of the neurons, \emph{(ii)} connectivity along a low-loss path, and \emph{(iii)} convergence to the global optimum. To achieve this goal, we take a mean-field view and relate the SHB dynamics to a certain partial differential equation in the limit of large network widths. This mean-field perspective has inspired a recent line of work focusing on SGD while, in contrast, our paper considers an algorithm with momentum. More specifically, after proving existence and uniqueness of the limit differential equations, we show convergence to the global optimum and give a quantitative bound between the mean-field limit and the SHB dynamics of a finite-width network. Armed with this last bound, we are able to establish the dropout-stability and connectivity of SHB solutions.}, author = {Wu, Diyuan and Kungurtsev, Vyacheslav and Mondelli, Marco}, booktitle = {Transactions on Machine Learning Research}, publisher = {ML Research Press}, title = {{Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence}}, year = {2023}, } @article{14949, abstract = {Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it remains an open question to which extent these models contribute to downstream classification performance. In particular, it remains unclear if they generalize enough to improve over directly using the additional data of their pre-training process for augmentation. We systematically evaluate a range of existing methods to generate images from diffusion models and study new extensions to assess their benefit for data augmentation. Personalizing diffusion models towards the target data outperforms simpler prompting strategies. However, using the pre-training data of the diffusion model alone, via a simple nearest-neighbor retrieval procedure, leads to even stronger downstream performance. Our study explores the potential of diffusion models in generating new training data, and surprisingly finds that these sophisticated models are not yet able to beat a simple and strong image retrieval baseline on simple downstream vision tasks.}, author = {Burg, Max and Wenzel, Florian and Zietlow, Dominik and Horn, Max and Makansi, Osama and Locatello, Francesco and Russell, Chris}, issn = {2835-8856}, journal = {Journal of Machine Learning Research}, publisher = {ML Research Press}, title = {{Image retrieval outperforms diffusion models on data augmentation}}, year = {2023}, } @inproceedings{14958, abstract = {Causal representation learning (CRL) aims at identifying high-level causal variables from low-level data, e.g. images. Current methods usually assume that all causal variables are captured in the high-dimensional observations. In this work, we focus on learning causal representations from data under partial observability, i.e., when some of the causal variables are not observed in the measurements, and the set of masked variables changes across the different samples. We introduce some initial theoretical results for identifying causal variables under partial observability by exploiting a sparsity regularizer, focusing in particular on the linear and piecewise linear mixing function case. We provide a theorem that allows us to identify the causal variables up to permutation and element-wise linear transformations in the linear case and a lemma that allows us to identify causal variables up to linear transformation in the piecewise case. Finally, we provide a conjecture that would allow us to identify the causal variables up to permutation and element-wise linear transformations also in the piecewise linear case. We test the theorem and conjecture on simulated data, showing the effectiveness of our method.}, author = {Xu, Danru and Yao, Dingling and Lachapelle, Sebastien and Taslakian, Perouz and von Kügelgen, Julius and Locatello, Francesco and Magliacane, Sara}, booktitle = {Causal Representation Learning Workshop at NeurIPS 2023}, location = {New Orleans, LA, United States}, publisher = {OpenReview}, title = {{A sparsity principle for partially observable causal representation learning}}, year = {2023}, } @unpublished{14961, abstract = {The use of simulated data in the field of causal discovery is ubiquitous due to the scarcity of annotated real data. Recently, Reisach et al., 2021 highlighted the emergence of patterns in simulated linear data, which displays increasing marginal variance in the casual direction. As an ablation in their experiments, Montagna et al., 2023 found that similar patterns may emerge in nonlinear models for the variance of the score vector $\nabla \log p_{\mathbf{X}}$, and introduced the ScoreSort algorithm. In this work, we formally define and characterize this score-sortability pattern of nonlinear additive noise models. We find that it defines a class of identifiable (bivariate) causal models overlapping with nonlinear additive noise models. We theoretically demonstrate the advantages of ScoreSort in terms of statistical efficiency compared to prior state-of-the-art score matching-based methods and empirically show the score-sortability of the most common synthetic benchmarks in the literature. Our findings remark (1) the lack of diversity in the data as an important limitation in the evaluation of nonlinear causal discovery approaches, (2) the importance of thoroughly testing different settings within a problem class, and (3) the importance of analyzing statistical properties in causal discovery, where research is often limited to defining identifiability conditions of the model. }, author = {Montagna, Francesco and Noceti, Nicoletta and Rosasco, Lorenzo and Locatello, Francesco}, booktitle = {arXiv}, title = {{Shortcuts for causal discovery of nonlinear models by score matching}}, doi = {10.48550/arXiv.2310.14246}, year = {2023}, } @unpublished{14962, abstract = {In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes objects in videos via a slot attention approach and then assigns text to the obtained slots. The latter is achieved by an unsupervised way to read localized semantic information from the pre-trained CLIP model. The resulting video object localization is entirely unsupervised apart from the implicit annotation contained in CLIP, and it is effectively the first unsupervised approach that yields good results on regular video benchmarks.}, author = {Fan, Ke and Bai, Zechen and Xiao, Tianjun and Zietlow, Dominik and Horn, Max and Zhao, Zixu and Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel and Shou, Mike Zheng and Locatello, Francesco and Schiele, Bernt and Brox, Thomas and Zhang, Zheng and Fu, Yanwei and He, Tong}, booktitle = {arXiv}, title = {{Unsupervised open-vocabulary object localization in videos}}, doi = {10.48550/arXiv.2309.09858}, year = {2023}, } @unpublished{14963, abstract = {Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers.}, author = {Zhao, Zixu and Wang, Jiaze and Horn, Max and Ding, Yizhuo and He, Tong and Bai, Zechen and Zietlow, Dominik and Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel and Shuai, Bing and Tu, Zhuowen and Brox, Thomas and Schiele, Bernt and Fu, Yanwei and Locatello, Francesco and Zhang, Zheng and Xiao, Tianjun}, booktitle = {arXiv}, title = {{Object-centric multiple object tracking}}, doi = {10.48550/arXiv.2309.00233}, year = {2023}, } @misc{14965, abstract = {A method of determining a correspondence between a first biological property of a cell and one or more further biological properties of cells is provided. The first biological property and the further biological properties are determined by different analysis techniques and each are contained in a respective one of a plurality of sets of biological properties. The method includes the steps of: converting the plurality of sets of biological properties into corresponding representations in a representation format which is invariant to the technologies used to derive the biological properties; determining, in said representation format, a representation from each of the converted sets of further biological properties which most closely matches the first representation of the first biological property; and re-converting the determined representations from the representation format back to the biological properties associated with the determined representations and thereby determining a correspondence between the first biological property and each of the further biological properties.}, author = {Ficek, Joanna and Lehmann, Kjong-Van and Locatello, Francesco and Raetsch, Gunnar and Stark, Stefan}, pages = {9}, title = {{Methods of determining correspondences between biological properties of cells}}, year = {2023}, } @inproceedings{14974, abstract = {The field of machine learning and AI has witnessed remarkable breakthroughs with the emergence of LLMs, which have also sparked a lively debate in the causal community. As researchers in this field, we are interested in exploring how LLMs relate to causality research, and how we can leverage the technology to advance it. In the second conference of Causal Learning and Reasoning (CLeaR), 2023, we held a round table discussion to gather and integrate the diverse perspectives of the CLeaR community on this topic. There is a general consensus that LLMs are not yet capable of causal reasoning at the current stage but has a lot of potential with public available information by CLeaR 2023. Enhancing causal machine learning is vital not only for its own sake but also to help LLMs improve their performance, especially regarding trustworthiness. In this document, we present both the summary and the raw outcome of the round table discussion. We acknowledge that with the progress of both fields, the opportunities and impact may rapidly change. We will repeat the same exercise in CLeaR 2024 to document the evolution.}, author = {Zhang, Cheng and Janzing, Dominik and van der Schaar, Mihaela and Locatello, Francesco and Spirtes, Peter and Zhang, Kun and Schölkopf, Bernhard and Uhler, Caroline}, booktitle = {2nd Conference on Causal Learning and Reasoning}, location = {Tübingen, Germany}, title = {{Causality in the time of LLMs: Round table discussion results of CLeaR 2023}}, year = {2023}, }