paper-with-me

홈 › Papers

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries

2021-04-16 · Arjun Nitin Bhagoji, Daniel Cullina, Vikash Sehwag, Prateek Mittal

Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it is critical to determine classifier-agnostic bounds on the training loss to establish when learning is possible. In this paper, we determine optimal lower bounds on the cross-entropy loss in the presence of test-time adversaries, along with the corresponding optimal classification outputs. Our formulation of the bound as a solution to an optimization problem is general enough to encompass any loss function depending on soft classifier outputs. We also propose and provide a proof of correctness for a bespoke algorithm to compute this lower bound efficiently, allowing us to determine lower bounds for multiple practical datasets of interest. We use our lower bounds as a diagnostic tool to determine the effectiveness of current robust training methods and find a gap from optimality at larger budgets. Finally, we investigate the possibility of using of optimal classification outputs as soft labels to empirically improve robust training.

📄 PDF Abstract BibTeX arXiv:2104.08382

Code (1)

arjunbhagoji/log-loss-lower-bounds 공식 구현 pytorch

Tasks

Diagnostic

Similar Papers 제목 키워드 기반

PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons

2020-06-16 · Xinjie Lan, Xin Guo, Kenneth E. Barner

We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspects: (i) MLPs formulate a family of Gibbs …

Generalization BoundsVariational Inference

Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions

2025-10-02 · Camilo Andrés García Trillos, Nicolás García Trillos arxiv

We consider adversarially robust classification in a multiclass setting under arbitrary loss functions and derive dual and barycentric reformulations of the corresponding learner-agnostic robust risk minimization problem…

Adversarial Robustness

Quantum Cross Entropy and Maximum Likelihood Principle

2021-02-23 · Zhou Shangnan, Yixu Wang

Quantum machine learning is an emerging field at the intersection of machine learning and quantum computing. Classical cross entropy plays a central role in machine learning. We define its quantum generalization, the qua…

BIG-bench Machine LearningQuantum Machine LearningRelation

Cross-Entropy Loss Functions: Theoretical Analysis and Applications

2023-04-14 · Anqi Mao, Mehryar Mohri, Yutao Zhong

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss applied to the outputs of a neural network, when the softmax is used. But, what guarantees can we rely on when using cross…

Adversarial Robustness

Continuity of Generalized Entropy and Statistical Learning

2020-12-31 · Aolin Xu

We study the continuity property of the generalized entropy as a function of the underlying probability distribution, defined with an action space and a loss function, and use this property to answer the basic questions …

Decision MakingLearning Theory