English
Related papers

Related papers: Local Optimality and Generalization Guarantees for…

200 papers

Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and in practice, these are obtained by MCMC algorithms such as…

Machine Learning · Computer Science 2021-04-23 Zhisheng Xiao , Qing Yan , Yali Amit

This paper studies the fundamental problem of learning deep generative models that consist of multiple layers of latent variables organized in top-down architectures. Such models have high expressivity and allow for learning hierarchical…

Machine Learning · Statistics 2020-07-21 Erik Nijkamp , Bo Pang , Tian Han , Linqi Zhou , Song-Chun Zhu , Ying Nian Wu

Empirical risk minimization (ERM) can be computationally expensive, with standard solvers scaling poorly even in the convex setting. We propose a novel lossless compression framework for convex ERM based on color refinement, extending prior…

Optimization and Control · Mathematics 2026-02-03 Bryan Zhu , Ziang Chen

Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood,…

Machine Learning · Computer Science 2026-05-01 Florian Wolf , Ilyas Fatkhullin , Niao He

We provide novel theoretical results regarding local optima of regularized $M$-estimators, allowing for nonconvexity in both loss and penalty functions. Under restricted strong convexity on the loss and suitable regularity conditions on the…

Statistics Theory · Mathematics 2015-01-05 Po-Ling Loh , Martin J. Wainwright

Our work is motivated by a desire to study the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as training of neural networks. The key insight, already…

Probability · Mathematics 2020-12-15 Kaitong Hu , Zhenjie Ren , David Siska , Lukasz Szpruch

Gradient Langevin dynamics and a variety of its variants have attracted increasing attention owing to their convergence towards the global optimal solution, initially in the unconstrained convex framework while recently even in convex…

Optimization and Control · Mathematics 2024-08-15 Kanji Sato , Akiko Takeda , Reiichiro Kawai , Taiji Suzuki

We study a natural extension of classical empirical risk minimization, where the hypothesis space is a random subspace of a given space. In particular, we consider possibly data dependent subspaces spanned by a random subset of the data,…

Machine Learning · Statistics 2022-12-09 Andrea Della Vecchia , Ernesto De Vito , Lorenzo Rosasco

Many optimization algorithms converge to stationary points. When the underlying problem is nonconvex, they may get trapped at local minimizers and occasionally stagnate near saddle points. We propose the Run-and-Inspect Method, which adds…

Optimization and Control · Mathematics 2018-07-02 Yifan Chen , Yuejiao Sun , Wotao Yin

Recently, it was demonstrated in [CS2012,CS2013] that the robustness of the classical Non-Local Means (NLM) algorithm [BCM2005] can be improved by incorporating $\ell^p (0 < p \leq 2)$ regression into the NLM framework. This general…

Computer Vision and Pattern Recognition · Computer Science 2015-06-15 Kunal N. Chaudhury

In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\geq 1$, i.e. functionals of the training data with low variance…

Machine Learning · Statistics 2019-01-25 Stéphan Clémençon , Aurélien Bellet , Igor Colin

Linear time series modelling is dominated by the use of purely autoregressive models even though incorporating moving average components can greatly improve parsimony. We present a convex formulation for vector-ARMA system identification…

Systems and Control · Electrical Eng. & Systems 2022-12-01 Alex Nguyen-Le , Victor M. Preciado

We study the problem of estimating Dynamic Discrete Choice (DDC) models, also known as offline Maximum Entropy-Regularized Inverse Reinforcement Learning (offline MaxEnt-IRL) in machine learning. The objective is to recover reward or $Q^*$…

Machine Learning · Computer Science 2026-05-06 Enoch H. Kang , Hema Yoganarasimhan , Lalit Jain

In this work we investigate to which extent one can recover class probabilities within the empirical risk minimization (ERM) paradigm. The main aim of our paper is to extend existing results and emphasize the tight relations between…

Machine Learning · Computer Science 2020-07-22 Alexander Mey , Marco Loog

Learning from temporally-correlated data is a core facet of modern machine learning. Yet our understanding of sequential learning remains incomplete, particularly in the multi-trajectory setting where data consists of many independent…

Machine Learning · Computer Science 2025-10-09 Eliot Shekhtman , Yichen Zhou , Ingvar Ziemann , Nikolai Matni , Stephen Tu

In this paper, we study the problem of sampling from a given probability density function that is known to be smooth and strongly log-concave. We analyze several methods of approximate sampling based on discretizations of the (highly…

Statistics Theory · Mathematics 2024-02-26 Arnak S. Dalalyan , Avetik G. Karagulyan

We study the design and implementation of numerical methods to solve the generalized Langevin equation (GLE) focusing on canonical sampling properties of numerical integrators. For this purpose, we cast the GLE in an extended phase space…

Numerical Analysis · Mathematics 2020-12-09 Benedict Leimkuhler , Matthias Sachs

The convergence of expectation-maximization (EM)-based algorithms typically requires continuity of the likelihood function with respect to all the unknown parameters (optimization variables). The requirement is not met when parameters…

Signal Processing · Electrical Eng. & Systems 2024-04-18 Geethu Joseph

The unadjusted Langevin algorithm is widely used for sampling from complex high-dimensional distributions. It is well known to be biased, with the bias typically scaling linearly with the dimension when measured in squared Wasserstein…

Machine Learning · Statistics 2025-09-11 Daniel Lacker , Fuzhong Zhou

We prove local convergence of several notable gradient descent algorithms used in machine learning, for which standard stochastic gradient descent theory does not apply directly. This includes, first, online algorithms for recurrent models…

Dynamical Systems · Mathematics 2021-01-11 Pierre-Yves Massé , Yann Ollivier
‹ Prev 1 4 5 6 7 8 10 Next ›