English
Related papers

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

200 papers

Stochastic first-order methods are standard for training large-scale machine learning models. Random behavior may cause a particular run of an algorithm to result in a highly suboptimal objective value, whereas theoretical guarantees are…

Optimization and Control · Mathematics 2024-09-02 Eduard Gorbunov , Marina Danilova , Innokentiy Shibaev , Pavel Dvurechensky , Alexander Gasnikov

Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators. We show that when the dataset…

Machine Learning · Computer Science 2021-08-17 Zhenyue Qin , Dongwoo Kim , Tom Gedeon

We analyze the properties of gradient descent on convex surrogates for the zero-one loss for the agnostic learning of linear halfspaces. If $\mathsf{OPT}$ is the best classification error achieved by a halfspace, by appealing to the notion…

Machine Learning · Computer Science 2021-02-16 Spencer Frei , Yuan Cao , Quanquan Gu

The efficiency of Monte Carlo samplers is dictated not only by energetic effects, such as large barriers, but also by entropic effects that are due to the sheer volume that is sampled. The latter effects appear in the form of an entropic…

Computational Physics · Physics 2009-11-13 Cristian Predescu

There is accumulating evidence in the literature that stability of learning algorithms is a key characteristic that permits a learning algorithm to generalize. Despite various insightful results in this direction, there seems to be an…

Machine Learning · Statistics 2019-05-10 Karim Abou-Moustafa , Csaba Szepesvari

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others,…

Machine Learning · Computer Science 2022-03-25 Ziqi Wang , Marco Loog

We study gradient descent (GD) with a constant stepsize for $\ell_2$-regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensure monotonic reduction of the optimization objective,…

Machine Learning · Statistics 2025-11-04 Jingfeng Wu , Pierre Marion , Peter Bartlett

Dark matter subhalos and satellite galaxies in state-of-the-art cosmological simulations still suffer from the ``overmerging'' problem, where inadequate force and/or mass resolution cause artificially enhanced tidal mass loss and premature…

Cosmology and Nongalactic Astrophysics · Physics 2026-01-16 Barry T. Chiang , Frank C. van den Bosch , Hsi-Yu Schive

We address the problem of minimizing a convex smooth function $f(x)$ over a compact polyhedral set $D$ given a stochastic zeroth-order constraint feedback model. This problem arises in safety-critical machine learning applications, such as…

Optimization and Control · Mathematics 2019-12-10 Ilnura Usmanova , Andreas Krause , Maryam Kamgarpour

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Yuchi Liu , Lei Wang , Yuli Zou , James Zou , Liang Zheng

Consider a network of $N$ decentralized computing agents collaboratively solving a nonconvex stochastic composite problem. In this work, we propose a single-loop algorithm, called DEEPSTORM, that achieves optimal sample complexity for this…

Optimization and Control · Mathematics 2023-04-14 Gabriel Mancino-Ball , Shengnan Miao , Yangyang Xu , Jie Chen

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Dmitrii Marin , Yuri Boykov

The gradient descent (GD) has been one of the most common optimizer in machine learning. In particular, the loss landscape of a neural network is typically sharpened during the initial phase of training, making the training dynamics hover…

Machine Learning · Statistics 2025-10-14 Han Bao , Shinsaku Sakaue , Yuki Takezawa

We develop a worst-case evaluation complexity bound for trust-region methods in the presence of unbounded Hessian approximations. We use the algorithm of arXiv:2103.15993v3 as a model, which is designed for nonsmooth regularized problems,…

Optimization and Control · Mathematics 2025-10-14 Geoffroy Leconte , Dominique Orban

Maximizing submodular objectives under constraints is a fundamental problem in machine learning and optimization. We study the maximization of a nonnegative, non-monotone $\gamma$-weakly DR-submodular function over a down-closed convex…

Machine Learning · Computer Science 2026-01-05 Hareshkumar Jadav , Ranveer Singh , Vaneet Aggarwal

Machine learning algorithms in high-dimensional settings are highly susceptible to the influence of even a small fraction of structured outliers, making robust optimization techniques essential. In particular, within the…

Machine Learning · Computer Science 2025-04-25 Changyu Gao , Andrew Lowy , Xingyu Zhou , Stephen J. Wright

The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints, under stochastic bandit feedback of rewards and safety risks of actions. We study the tradeoffs…

Machine Learning · Computer Science 2024-07-02 Aditya Gangrade , Tianrui Chen , Venkatesh Saligrama

We study the complexity of approximating integrals of smooth functions at absolute precision $\varepsilon > 0$ with confidence level $1 - \delta \in (0,1)$. The optimal error rate for multivariate functions from classical isotropic Sobolev…

Numerical Analysis · Mathematics 2018-09-27 Robert J. Kunsch , Daniel Rudolf

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

Machine Learning · Computer Science 2026-04-13 Matheus Vinícius Todescato , Joel Luís Carbonera

We propose a general approach for encouraging fairness in survival analysis models based on minimizing a worst-case error across all subpopulations that occur with at least a user-specified probability. This approach can be used to convert…

Machine Learning · Statistics 2024-09-18 Shu Hu , George H. Chen
‹ Prev 1 4 5 6 7 8 10 Next ›