paper-with-me

Papers

Probabilistic Invariant Learning with Randomized Linear Classifiers

2023-08-08 · NeurIPS 2023 11

Designing models that are both expressive and preserve known invariances of tasks is an increasingly hard problem. Existing solutions tradeoff invariance for computational or memory resources. In this work, we show how to leverage randomness and design models that are both expressive and invariant but use less resources. Inspired by randomized algorithms, our key insight is that accepting probabilistic notions of universal approximation and invariance can reduce our resource requirements. More specifically, we propose a class of binary classification models called Randomized Linear Classifiers (RLCs). We give parameter and sample size conditions in which RLCs can, with high probability, approximate any (smooth) function while preserving invariance to compact group transformations. Leveraging this result, we design three RLCs that are provably probabilistic invariant for classification tasks over sets, graphs, and spherical data. We show how these models can achieve probabilistic invariance and universality using less resources than (deterministic) neural networks and their invariant counterparts. Finally, we empirically demonstrate the benefits of this new class of models on invariant tasks where deterministic invariant neural networks are known to struggle.

📄 PDF Abstract BibTeX arXiv:2308.04412

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification

Similar Papers 제목 키워드 기반

On the Role of Randomization in Adversarially Robust Classification

2023-02-14 · NeurIPS 2023 11

Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed as an alternative to deterministic ones…

Robust classification

Certified Robustness to Label-Flipping Attacks via Randomized Smoothing

2020-02-07 · ICML 2020 1 · Elan Rosenfeld, Ezra Winston, Pradeep Ravikumar, J. Zico Kolter

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying …

Data PoisoningGeneral ClassificationMulti-class Classification

Randomized multi-class classification under system constraints: a unified approach via post-processing

2025-12-16 · Evgenii Chzhen, Mohamed Hebiri, Gayane Taturyan arxiv

We study the problem of multi-class classification under system-level constraints expressible as linear functionals over randomized classifiers. We propose a post-processing approach that adjusts a given base classifier …

Multi-class Classification

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

2021-05-09 · Zehao Xiao, Jiayi Shen, XianTong Zhen, Ling Shao 외

Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on vari…

Bayesian InferenceDomain Generalization

Building an Ensemble of Classifiers via Randomized Models of Ensemble Members

2021-09-16 · Pawel Trajdos, Marek Kurzynski

Many dynamic ensemble selection (DES) methods are known in the literature. A previously-developed by the authors, method consists in building a randomized classifier which is treated as a model of the base classifier. Th…