arXiv research

Greedy algorithm achieves sublinear regret for various distributions.

Study provides bounds for estimating intrinsic dimension using Gaussian kernels.

New method certifies anti-concentration for various non-Gaussian distributions.

Robustly learns Ising models with corrupted data.

Improved subspace recovery algorithm with dimension-independent error and polynomial time.

Low-degree method fails to predict robust subspace recovery problem.

We give the first polynomial-time algorithm for robust regression in the list-decodable setting where an adversary can corrupt a greater than $1/2$ fraction of examples. For any $α< 1$, our algorithm takes as input a sample $\{(x_i,y_i)\}_{i \leq n}$ of $n$ linear equations where $αn$ of the equations satisfy $y_i = \l…

Robustly clusters mixtures of Gaussians even with outliers.

Improved Lasso estimator speeds up variable selection.

We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities. We also demonstrate our concentration bounds to be optimal with a matching anti-concentration inequality, proved using the same method. Together these constitute a finite-time versi…

Sharp concentration bounds for i.i.d. variables.

OPSRL algorithm reduces regret with few samples in reinforcement learning.

Adversarial training improves robustness of halfspaces in noisy data.

Bayes-UCBVI tackles reinforcement learning with a new upper confidence bound method.

Algorithm learns Gaussian mixtures robust to outliers.

Paper addresses concentration of distances for fractional quasi p-norms, identifying conditions for concentration and anti-concentration.

In this article, we investigate large sample properties of model selection procedures in a general Bayesian framework when a closed form expression of the marginal likelihood function is not available or a local asymptotic quadratic approximation of the log-likelihood function does not exist. Under appropriate identifi…

Fictitious play is a simple and widely studied adaptive heuristic for playing repeated games. It is well known that fictitious play fails to be Hannan consistent. Several variants of fictitious play including regret matching, generalized regret matching and smooth fictitious play, are known to be Hannan consistent. In …

Polynomial-time algorithm for estimating covariance in corrupted Gaussian data.

Several fundamental problems that arise in optimization and computer science can be cast as follows: Given vectors $v_1,\ldots,v_m \in \mathbb{R}^d$ and a constraint family ${\cal B}\subseteq 2^{[m]}$, find a set $S \in \cal{B}$ that maximizes the squared volume of the simplex spanned by the vectors in $S$. A motivatin…

We propose a new online algorithm for cumulative regret minimization in a stochastic linear bandit. The algorithm pulls the arm with the highest estimated reward in a linear model trained on its perturbed history. Therefore, we call it perturbed-history exploration in a linear bandit (LinPHE). The perturbed history is …

New algorithm learns halfspaces with noise using Forster decomposition.

AdaBoost improves binary classification in robust one-bit compressed sensing with adversarial errors.

The paper explores how linear neural networks can overfit without bias when data is well-behaved.

Study on ReLU regression with Massart noise, achieving exact parameter recovery.

The paper analyzes tensor recovery from symmetric rank-one measurements using information theory.

Max-affine regression method converges linearly using GD and SGD.

We solve ReLU regression with efficient approximations for various distributions.

Efficient algorithm for near-optimal online learning with generalized linear functions.

Paper proposes Sp-GD for sparse max-affine regression with theoretical guarantees.

Paper proposes a new RLHF framework for human preference learning.

Algorithm learns halfspaces in noisy data efficiently.

Self-training improves weak classifiers in mixture models.

Two preprocessing techniques reduce neural network training cost.

This work proposes efficient classical training protocols for IQP circuits to train quantum generative models.

A new method reduces the bias in estimating inverse covariance matrices from sketches.

We study locally compact contractive local groups, that is, locally compact local groups with a contractive pseudo-automorphism. We prove that if such an object is locally connected, then it is locally isomorphic to a Lie group. We also prove a related structure theorem for locally compact contractive local groups whic…

Every locally compact local group is locally isomorphic to a topological group.

Generalizing the notion of local $φ$-symmetry of Takahashi, in the present paper, we introduce the notion of local $φ$-semisymmetry of a Sasakian manifold along with its proper existence and characterization. We also study the notion of local Ricci (resp., projective, conformal) $φ$-semisymmetry of a Sasakian manifold …

Local Gradient Descent with local steps converges to the centralized model in the interpolation regime.

Positive simplicial volume implies locally symmetric space structure.

We introduce the notion of a local torus action modeled on the standard representation (for simplicity, we call it a local torus action). It is a generalization of a locally standard torus action and also an underlying structure of a locally toric Lagrangian fibration. For a local torus action, we define two invariants…

We modify previous quasi-local mass definition. The new definition provides expressions of the quasi-local energy, the quasi-local linear momentum and the quasi-local mass. And they are equal to the ADM expressions at spatial infinity. Moreover, the new quasi-local energy has the positivity property.

Localized diffusion models reduce training complexity by exploiting low-dimensional structure.

Generalizes machine learning models using localization kernels and local means.

This paper explores estimating chaotic dynamics and parameters using local ensemble Kalman filters.

We give a description of local and global moves on a class of locally planar trivalent graphs and we show that it contains $λ$-Scale calculus, therefore in particular untyped lambda calculus. Surprisingly, the beta reduction rule comes from a local "sewing" transformation of trivalent locally planar graphs.

Local mass perspective on Bayesian inference