← Back to all news
arXiv Machine Learning By Andrea Montanari, Basil Saeed

Universality of empirical risk minimization

Read the original on arXiv Machine Learning →

arXiv:2202. 08832v3 Announce Type: replace-cross Abstract: We study a general class of optimization problems with decision variable $\boldsymbol{\Theta} \in \mathbb{R}^{p \times k}$ and cost function which is the sum of $n$ terms, each dependent on $\boldsymbol{\Theta}$ through the $k$-dimensional projection $\boldsymbol{\Theta}^\top \boldsymbol{x}_i$, where $\boldsymbol{x}_i$, $i \leq n$ are i.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 11

Constrained Learning with Universally Learnable Concept Classes

arXiv:2608. 08414v1 Announce Type: new Abstract: We study constrained statistical learning over infinite-dimensional hypothesis classes in the fully nonconvex setting, and establish universal PACC learnability of the solutions of dual algorithms: Probably Approximately Correct on Constraints, guaranteeing optimality and constraint satisfaction at once.

By Herlock SeyedAbolfazl Rahimi, Spyridon Pougkakiotis, Dionysis Kalogerias
More like this →
arXiv Machine Learning
Jun 2

Robust Learning of a Group DRO Neuron

arXiv:2601. 18115v2 Announce Type: replace Abstract: We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional shifts, for a broad family of covariate distributions.

By Guyang Cao, Shuyao Li, Sushrut Karmalkar, Jelena Diakonikolas
llmsbenchmarks
More like this →
arXiv Machine Learning
Jun 19

Fisher-Geometric Sharpness and the Implicit Bias of SGD toward Flat Minima

arXiv:2606. 20469v1 Announce Type: new Abstract: A widely held intuition in deep learning is that stochastic gradient descent (SGD) implicitly favors flat minima and that flat minima generalize better, but standard Euclidean measures of flatness such as the trace or maximum eigenvalue of the loss Hessian are not invariant under reparametrizations that preserve the network function, which undermines the theoretical foundations of this narrative.

By Md Sakir Ahmed, Kumaresh Sarmah, Hemen Dutta
safety
More like this →