Omnipredicting Single-Index Models with Multi-Index Models
Recent work on supervised learning [GKR+ 22] defined the notion of omnipredictors, ie,
predictor functions $ p $ over features that are simultaneously competitive for minimizing a …
predictor functions $ p $ over features that are simultaneously competitive for minimizing a …
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
A single-index model (SIM) is a function of the form $\sigma (\mathbf {w}^{\ast}\cdot\mathbf
{x}) $, where $\sigma:\mathbb {R}\to\mathbb {R} $ is a known link function and $\mathbf …
{x}) $, where $\sigma:\mathbb {R}\to\mathbb {R} $ is a known link function and $\mathbf …
Learning noisy halfspaces with a margin: Massart is no harder than random
G Chandrasekaran, V Kontonis, K Stavropoulos… - arxiv preprint arxiv …, 2025 - arxiv.org
We study the problem of PAC learning $\gamma $-margin halfspaces with Massart noise.
We propose a simple proper learning algorithm, the Perspectron, that has sample …
We propose a simple proper learning algorithm, the Perspectron, that has sample …
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
We study the problem of learning a single neuron with respect to the $ L_2^ 2$-loss in the
presence of adversarial distribution shifts, where the labels can be arbitrary, and the goal is …
presence of adversarial distribution shifts, where the labels can be arbitrary, and the goal is …
Robustly Learning Monotone Generalized Linear Models via Data Augmentation
N Zarifis, P Wang, I Diakonikolas… - arxiv preprint arxiv …, 2025 - arxiv.org
We study the task of learning Generalized Linear models (GLMs) in the agnostic model
under the Gaussian distribution. We give the first polynomial-time algorithm that achieves a …
under the Gaussian distribution. We give the first polynomial-time algorithm that achieves a …
Convergence of for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
I Anagnostides, T Sandholm - arxiv preprint arxiv:2410.21636, 2024 - arxiv.org
Gradient-based algorithms have shown great promise in solving large (two-player) zero-sum
games. However, their success has been mostly confined to the low-precision regime since …
games. However, their success has been mostly confined to the low-precision regime since …