paper-with-me

홈 › Papers

Agnostically Learning Single-Index Models using Omnipredictors

2023-06-18 · NeurIPS 2023 11

We give the first result for agnostically learning Single-Index Models (SIMs) with arbitrary monotone and Lipschitz activations. All prior work either held only in the realizable setting or required the activation to be known. Moreover, we only require the marginal to have bounded second moments, whereas all prior work required stronger distributional assumptions (such as anticoncentration or boundedness). Our algorithm is based on recent work by [GHK$^+$23] on omniprediction using predictors satisfying calibrated multiaccuracy. Our analysis is simple and relies on the relationship between Bregman divergences (or matching losses) and $\ell_p$ distances. We also provide new guarantees for standard algorithms like GLMtron and logistic regression in the agnostic setting.

📄 PDF Abstract BibTeX arXiv:2306.10615

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

Omnipredicting Single-Index Models with Multi-Index Models

2024-11-20 · Lunjia Hu, Kevin Tian, Chutong Yang

Recent work on supervised learning [GKR+22] defined the notion of omnipredictors, i.e., predictor functions $p$ over features that are simultaneously competitive for minimizing a family of loss functions $\mathcal{L}$ ag…

Learning Theory

Agnostically Learning Multi-index Models with Queries

2023-12-27 · Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis, Christos Tzamos 외

We study the power of query access for the task of agnostic learning under the Gaussian distribution. In the agnostic model, no assumptions are made on the labels and the goal is to compute a hypothesis that is competiti…

Dimensionality Reduction

Omnipredictors for Constrained Optimization

2022-09-15 · Lunjia Hu, Inbal Livni-Navon, Omer Reingold, Chutong Yang

The notion of omnipredictors (Gopalan, Kalai, Reingold, Sharan and Wieder ITCS 2021), suggested a new paradigm for loss minimization. Rather than learning a predictor based on a known loss function, omnipredictors can ea…

Fairness

Omnipredictors for Regression and the Approximate Rank of Convex Functions

2024-01-26 · Parikshit Gopalan, Princewill Okoroafor, Prasad Raghavendra, Abhishek Shetty 외

Consider the supervised learning setting where the goal is to learn to predict labels $\mathbf y$ given points $\mathbf x$ from a distribution. An \textit{omnipredictor} for a class $\mathcal L$ of loss functions and a c…

regression

Omnipredictors

2021-09-11 · Parikshit Gopalan, Adam Tauman Kalai, Omer Reingold, Vatsal Sharan 외

Loss minimization is a dominant paradigm in machine learning, where a predictor is trained to minimize some loss function that depends on an uncertain event (e.g., "will it rain tomorrow?''). Different loss functions imp…

Fairness