English
Related papers

Related papers: Approximate Heavy Tails in Offline (Multi-Pass) St…

200 papers

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

Machine Learning · Computer Science 2018-01-17 Pratik Chaudhari , Stefano Soatto

Recent theoretical and empirical successes in deep learning, including the celebrated neural scaling laws, are punctuated by the observation that many objects of interest tend to exhibit some form of heavy-tailed or power law behavior. In…

Machine Learning · Statistics 2025-06-05 Liam Hodgkinson , Zhichao Wang , Michael W. Mahoney

This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD). Building on the recent work of Ben Arous, Gheissari, and Jagannath on the effective dynamics of SGD, we study the critical scaling regime of…

Machine Learning · Statistics 2026-05-01 Parsa Rangriz

Deep neural networks have revolutionized machine learning, yet their training dynamics remain theoretically unclear-we develop a continuous-time, matrix-valued stochastic differential equation (SDE) framework that rigorously connects the…

Machine Learning · Computer Science 2026-02-10 Brian Richard Olsen , Sam Fatehmanesh , Frank Xiao , Adarsh Kumarappan , Anirudh Gajula

Modelling excesses over a high threshold using the Pareto or generalized Pareto distribution (PD/GPD) is the most popular approach in extreme value statistics. This method typically requires high thresholds in order for the (G)PD to fit…

Statistics Theory · Mathematics 2009-01-13 Jan Beirlant , Elisabeth Joossens , Johan Segers

Neural scaling laws suggest that the test error of large language models trained online decreases polynomially as the model size and data size increase. However, such scaling can be unsustainable when running out of new data. In this work,…

Machine Learning · Computer Science 2025-09-26 Licong Lin , Jingfeng Wu , Peter L. Bartlett

Traditional implicit generative models are capable of learning highly complex data distributions. However, their training involves distinguishing real data from synthetically generated data using adversarial discriminators, which can lead…

Machine Learning · Computer Science 2025-09-05 José Manuel de Frutos , Manuel A. Vázquez , Pablo Olmos , Joaquín Míguez

Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergence, generates samples from a stationary distribution. We show…

Machine Learning · Statistics 2017-09-12 Stephan Mandt , Matthew D. Hoffman , David M. Blei

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes. Recent methods propose to rebalance classes but…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Weiqi Li , Fan Lyu , Fanhua Shang , Liang Wan , Wei Feng

Economically responsible mitigation of multivariate extreme risks-such as extreme rainfall over large areas, large simultaneous variations in many stock prices, or widespread breakdowns in transportation systems-requires assessing the…

Machine Learning · Statistics 2026-01-13 Stéphane Lhaut , Holger Rootzén , Johan Segers

We study a heavily overloaded single-server queue with abandonment and derive bounds on stationary tail probabilities of the queue length. As the abandonment rate $\gamma \downarrow 0$, the centered-scaled queue length $\tilde{q}$ is known…

Probability · Mathematics 2026-03-20 Zedong Wang , Siva Theja Maguluri

Stochastic Gradient Descent (SGD) is widely used in machine learning problems to efficiently perform empirical risk minimization, yet, in practice, SGD is known to stall before reaching the actual minimizer of the empirical risk. SGD…

Machine Learning · Statistics 2017-02-09 Vivak Patel

This note presents an operational measure of fat-tailedness for univariate probability distributions, in $[0,1]$ where 0 is maximally thin-tailed (Gaussian) and 1 is maximally fat-tailed. Among others,1) it helps assess the sample size…

Methodology · Statistics 2019-04-30 Nassim Nicholas Taleb

Skewness and non-Gaussian behavior are essential features of the distribution of short-scale velocity increments in isotropic turbulent flows. Yet, although the skewness has been generally linked to time-reversal symmetry breaking and…

Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to…

Optimization and Control · Mathematics 2020-10-01 Iman Shames , Farhad Farokhi

Stochastic gradient descent (SGD) is a powerful optimization technique that is particularly useful in online learning scenarios. Its convergence analysis is relatively well understood under the assumption that the data samples are…

Machine Learning · Computer Science 2024-10-03 Ethan Che , Jing Dong , Xin T. Tong

Unraveling the reasons behind the remarkable success and exceptional generalization capabilities of deep neural networks presents a formidable challenge. Recent insights from random matrix theory, specifically those concerning the spectral…

Machine Learning · Statistics 2023-04-10 Xuanzhe Xiao , Zeng Li , Chuanlong Xie , Fengwei Zhou

Preferential attachment is widely used to model power-law behavior of degree distributions in both directed and undirected networks. In a directed preferential attachment model, despite the well-known marginal power-law degree…

Probability · Mathematics 2018-08-07 Tiandong Wang , Sidney I. Resnick

We consider the task of heavy-tailed statistical estimation given streaming $p$-dimensional samples. This could also be viewed as stochastic optimization under heavy-tailed distributions, with an additional $O(p)$ space complexity…

Machine Learning · Computer Science 2022-02-28 Che-Ping Tsai , Adarsh Prasad , Sivaraman Balakrishnan , Pradeep Ravikumar

We provide upper bounds on the end-to-end backlog and delay in a network with heavy-tailed and self-similar traffic. The analysis follows a network calculus approach where traffic is characterized by envelope functions and service is…

Networking and Internet Architecture · Computer Science 2013-12-30 Jorg Liebeherr , Almut Burchard , Florin Ciucu
‹ Prev 1 4 5 6 7 8 10 Next ›