English
Related papers

Related papers: Non-Boolean OMv: One More Reason to Believe Lower …

200 papers

The constrained gradient method (CGM) has recently been proposed to solve convex optimization and monotone variational inequality (VI) problems with general functional constraints. While existing literature has established convergence…

Optimization and Control · Mathematics 2025-11-24 Danqing Zhou , Hongmei Chen , Shiqian Ma , Junfeng Yang

Reinforcement Learning is a powerful framework for training agents to navigate different situations, but it is susceptible to changes in environmental dynamics. However, solving Markov Decision Processes that are robust to changes is…

Machine Learning · Computer Science 2024-06-21 Etash Kumar Guha

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Damien Teney , Peng Wang , Jiewei Cao , Lingqiao Liu , Chunhua Shen , Anton van den Hengel

The standard algorithms for solving large-scale convex-concave saddle point problems, or, more generally, variational inequalities with monotone operators, are proximal type algorithms which at every iteration need to compute a…

Optimization and Control · Mathematics 2014-06-24 Anatoli Juditsky , Arkadi Nemirovski

Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy. Most of these optimization problems are NP-hard and computationally demanding, often requiring approximate solutions for…

Optimization and Control · Mathematics 2021-06-23 James Kotary , Ferdinando Fioretto , Pascal Van Hentenryck

Despite the recent development in machine learning, most learning systems are still under the concept of "black box", where the performance cannot be understood and derived. With the rise of safety and privacy concerns in public, designing…

Machine Learning · Computer Science 2023-06-30 Shuai Zhang

A deep learning-based computational method is proposed for soft matter dynamics -- the deep Onsager-Machlup method (DOMM). It combines the brute forces of deep neural networks (DNNs) with the fundamental physics principle -- Onsager-Machlup…

Soft Condensed Matter · Physics 2025-11-24 Zhihao Li , Boyi Zou , Haiqin Wang , Jian Su , Dong Wang , Xinpeng Xu

The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well. This paper provides convex lower bounds and concave upper bounds on the softmax function, which are compatible…

Machine Learning · Computer Science 2023-03-06 Dennis Wei , Haoze Wu , Min Wu , Pin-Yu Chen , Clark Barrett , Eitan Farchi

Deep latent variable models (DLVMs) combine the approximation abilities of deep neural networks and the statistical foundations of generative models. Variational methods are commonly used for inference; however, the exact likelihood of…

Machine Learning · Statistics 2018-06-29 Pierre-Alexandre Mattei , Jes Frellsen

We introduce the concept of strong high-order approximate minimizers for nonconvex optimization problems. These apply in both standard smooth and composite non-smooth settings, and additionally allow convex or inexpensive constraints. An…

Optimization and Control · Mathematics 2020-01-30 Coralia Cartis , Nick Gould , Philippe L. Toint

During recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimization methods has been growing. One of the main reasons for this is that high-probability complexity…

First of all we give some reasons that "natural proofs" built not a barrier to prove P $\not=$ NP using Boolean complexity. Then we investigate the approximation method for its extension to prove super-polynomial lower bounds for the…

Computational Complexity · Computer Science 2020-06-16 Norbert Blum

We prove a lower bound $\Omega\left(\frac{k+l}{k^2l^2}N^{2-\frac{k+l+2}{kl}}\right)$ on the maximal possible weight of a $(k,l)$-free (that is, free of all-ones $k\times l$ submatrices) Boolean circulant $N \times N$ matrix. The bound is…

Computational Complexity · Computer Science 2017-01-31 M. I. Grinchuk , I. S. Sergeev

Boosting is a celebrated machine learning approach which is based on the idea of combining weak and moderately inaccurate hypotheses to a strong and accurate one. We study boosting under the assumption that the weak hypotheses belong to a…

Machine Learning · Computer Science 2024-02-14 Noga Alon , Alon Gonen , Elad Hazan , Shay Moran

Implicit variables of a mathematical program are variables which do not need to be optimized but are used to model feasibility conditions. They frequently appear in several different problem classes of optimization theory comprising bilevel…

Optimization and Control · Mathematics 2023-06-22 Matúš Benko , Patrick Mehlitz

Observable operator models (OOMs) offer a powerful framework for modelling stochastic processes, surpassing the traditional hidden Markov models (HMMs) in generality and efficiency. However, using OOMs to model infinite-dimensional…

Probability · Mathematics 2024-04-19 Wojciech Anyszka

This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline RL is the appropriate model for almost any real-life ML…

Machine Learning · Computer Science 2025-01-07 Ming Yin , Mengdi Wang , Yu-Xiang Wang

Recent successes of game-theoretic formulations in ML have caused a resurgence of research interest in differentiable games. Overwhelmingly, that research focuses on methods and upper bounds on their speed of convergence. In this work, we…

Machine Learning · Computer Science 2020-09-16 Adam Ibrahim , Waïss Azizian , Gauthier Gidel , Ioannis Mitliagkas

A dynamic graph algorithm is a data structure that answers queries about a property of the current graph while supporting graph modifications such as edge insertions and deletions. Prior work has shown strong conditional lower bounds for…

Data Structures and Algorithms · Computer Science 2023-01-30 Monika Henzinger , Ami Paz , A. R. Sricharan

We revisit the theory of importance weighted variational inference (IWVI), a promising strategy for learning latent variable models. IWVI uses new variational bounds, known as Monte Carlo objectives (MCOs), obtained by replacing intractable…

Machine Learning · Statistics 2022-01-27 Pierre-Alexandre Mattei , Jes Frellsen