English
Related papers

Related papers: Ghosts of Softmax: Complex Singularities That Limi…

200 papers

We consider the problem of stochastic convex optimization with exp-concave losses using Empirical Risk Minimization in a convex class. Answering a question raised in several prior works, we provide a $O( d / n + \log( 1 / \delta) / n )$…

Machine Learning · Computer Science 2023-07-06 Nikita Puchkin , Nikita Zhivotovskiy

This work develops novel error expansions with computable leading order terms for the global weak error in the tau-leap discretization of pure jump processes arising in kinetic Monte Carlo models. Accurate computable a posteriori error…

Numerical Analysis · Mathematics 2011-10-21 Jesper Karlsson , Raul Tempone

Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms.…

Computer Vision and Pattern Recognition · Computer Science 2020-05-29 Yang Chen , Zongqing Lu , Xuechen Zhang , Lei Chen , Qingmin Liao

The margin-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Moreover,…

Computer Vision and Pattern Recognition · Computer Science 2019-12-18 JT Wu , L. Wang

The bidirected cut relaxation is the characteristic representative of the bidirected relaxations ($\mathrm{\mathcal{BCR}}$) which are a well-known class of equivalent LP-relaxations for the NP-hard Steiner Tree Problem in Graphs (STP).…

Data Structures and Algorithms · Computer Science 2020-02-20 Robert Vicari

We study the type of solutions to which stochastic gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. Our results are based on a dynamical stability analysis. In the…

Machine Learning · Computer Science 2023-07-03 Mor Shpigel Nacson , Rotem Mulayoff , Greg Ongie , Tomer Michaeli , Daniel Soudry

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic…

Machine Learning · Computer Science 2024-12-09 Hossein Taheri , Christos Thrampoulidis , Arya Mazumdar

Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progress has been made in understanding grokking, the reasons…

Machine Learning · Computer Science 2025-05-20 Lucas Prieto , Melih Barsbey , Pedro A. M. Mediano , Tolga Birdal

We develop a trust-region method for minimizing the sum of a smooth term $f$ and a nonsmooth term $h$), both of which can be nonconvex. Each iteration of our method minimizes a possibly nonconvex model of $f + h$ in a trust region. The…

Optimization and Control · Mathematics 2021-08-04 Aleksandr Y. Aravkin , Robert Baraldi , Dominique Orban

The \emph{strong collapse} of a simplicial complex, proposed by Barmak and Minian (\emph{Disc. Comp. Geom. 2012}), is a combinatorial collapse of a complex onto its sub-complex. Recently, it has received attention from computational…

Computational Geometry · Computer Science 2023-01-10 Jean-Daniel Boissonnat , Kunal Dutta , Soumik Dutta , Siddharth Pritam

We consider solving the $\ell_1$-regularized least-squares ($\ell_1$-LS) problem in the context of sparse recovery, for applications such as compressed sensing. The standard proximal gradient method, also known as iterative…

Optimization and Control · Mathematics 2012-03-15 Lin Xiao , Tong Zhang

It is known that maximal entropy random walks and partition functions that count long paths on graphs tend to become localized near nodes with a high degree. Here, we revisit the simplest toy model of such a localization: a regular tree of…

Statistical Mechanics · Physics 2023-09-22 Alexey V. Gulyaev , Mikhail V. Tamm

We propose to determine the optimal softening length in N-body halo simulations by minimizing the ensemble-average acceleration error at a small radius r0. This strategy ensures that the error never exceeds the optimal value beyond r0.…

Astrophysics · Physics 2009-11-13 Hu Zhan

The best techniques for the constrained maximum-entropy sampling problem, a discrete-optimization problem arising in the design of experiments, are via a variety of concave continuous relaxations of the objective function. A standard…

Optimization and Control · Mathematics 2023-02-13 Zhongzhu Chen , Marcia Fampa , Jon Lee

Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient…

Optimization and Control · Mathematics 2026-04-09 Hong T. M. Chu

Finite-sum optimization plays an important role in the area of machine learning, and hence has triggered a surge of interest in recent years. To address this optimization problem, various randomized incremental gradient methods have been…

Machine Learning · Computer Science 2022-06-22 Min Zhang , Yao Shu , Kun He

Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost…

Machine Learning · Statistics 2020-02-18 Robert Bamler , Stephan Mandt

Evaluating the log-sum-exp function or the softmax function is a key step in many modern data science algorithms, notably in inference and classification. Because of the exponentials that these functions contain, the evaluation is prone to…

Numerical Analysis · Mathematics 2019-09-10 Pierre Blanchard , Desmond J. Higham , Nicholas J. Higham

Soft extrapolation refers to the problem of recovering a function from its samples, multiplied by a fast-decaying window and perturbed by an additive noise, over an interval which is potentially larger than the essential support of the…

Numerical Analysis · Mathematics 2018-12-26 Dmitry Batenkov , Laurent Demanet , Hrushikesh N. Mhaskar

Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations that scale linearly with the number of output classes, which can restrict the size…

Machine Learning · Computer Science 2016-05-30 Alexandre de Brébisson , Pascal Vincent