A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study improves understanding of why agentic theorem provers succeed.
This thesis improves practical reinforcement learning methods with robustness, scalability, and efficiency.
Framework for fair classification with noisy protected attributes and provable guarantees.
A new principle and method improve out-of-distribution detection in generative models.
Paper resolves bias in ALFT training using generalized alignment games.
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…
This paper concerns dictionary learning, i.e., sparse coding, a fundamental representation learning problem. We show that a subgradient descent algorithm, with random initialization, can provably recover orthogonal dictionaries on a natural nonsmooth, nonconvex minimization formulation of the problem, under mi…
New algorithm finds near-optimal policies efficiently in zero-sum games.
Paper analyzes distributional reinforcement learning with value function approximation, introducing Bellman unbiasedness and a new algorithm.
We analyze a simple prefiltered variation of the least squares estimator for the problem of estimation with biased, semi-parametric noise, an error model studied more broadly in causal statistics and active learning. We prove an oracle inequality which demonstrates that this procedure provably mitigates the variance in…
Layer-wise preconditioning methods improve neural network optimization and feature learning.
New offline RL algorithms tackle partial data coverage with optimal performance and practicality.
Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier features are still not well understood. In this paper we take steps toward filling this gap. Specifica…
Ridge leverage scores provide a balance between low-rank approximation and regularization, and are ubiquitous in randomized linear algebra and machine learning. Deterministic algorithms are also of interest in the moderately big data regime, because deterministic algorithms provide interpretability to the practitioner …
Guarantees for third-person imitation learning from offline data.
Paper develops efficient algorithms for robust distributed learning with statistical guarantees.
We develop efficient algorithms to estimate the stability of Ordinary Least Squares regression results.
Paper reconstructs training data from a single gradient query.
We provide initial seedings to the Quick Shift clustering algorithm, which approximate the locally high-density regions of the data. Such seedings act as more stable and expressive cluster-cores than the singleton modes found by Quick Shift. We establish statistical consistency guarantees for this modification. We then…
Efficiently bootstraps massive distributed data without over-resampling.
Generalized Linear Models (GLMs) and Single Index Models (SIMs) provide powerful generalizations of linear regression, where the target variable is assumed to be a (possibly unknown) 1-dimensional function of a linear predictor. In general, these problems entail non-convex estimation procedures, and, in practice, itera…
ParK efficiently solves kernel ridge regression for large datasets.
Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational …
Paper develops algorithms for nonsmooth, nonconvex statistical learning problems.
Efficient offline reinforcement learning with neural networks using differentiable function approximation.
Statistical guarantees for hyperparameter selection
New stable HOIF estimators for statistical functionals.
Combines public and private data for better statistical estimation.
Nonconvex optimization problems arise in different research fields and arouse lots of attention in signal processing, statistics and machine learning. In this work, we explore the accelerated proximal gradient method and some of its variants which have been shown to converge under nonconvex context recently. We show th…
New framework for fair classification in adversarial settings with provable guarantees.
Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such as hyper-spectral imaging or blood glucose monitoring), only an incomplete fraction of the data entries may be available. For incomplete sett…
We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' tr…
New algorithm for weighted low rank approximation with provable guarantees.
We solve ElasticNet regularization tuning across multiple instances with provable guarantees.
Backdoors in deep neural networks are undetectable and enable invariance-based adversarial examples.
We propose a nonconvex estimator for joint multivariate regression and precision matrix estimation in the high dimensional regime, under sparsity constraints. A gradient descent algorithm with hard thresholding is developed to solve the nonconvex estimator, and it attains a linear rate of convergence to the true regres…
Recovering matrices from compressive and grossly corrupted observations is a fundamental problem in robust statistics, with rich applications in computer vision and machine learning. In theory, under certain conditions, this problem can be solved in polynomial time via a natural convex relaxation, known as Compressive …
New theory allows ICA without assuming non-Gaussian sources.
Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms. We address this problem through the principled lens of distributionally robust optimization, which guarantees performance under adversarial input perturbations. By considering a Lagrangian …
We propose a novel sparse tensor decomposition method, namely Tensor Truncated Power (TTP) method, that incorporates variable selection into the estimation of decomposition components. The sparsity is achieved via an efficient truncation step embedded in the tensor power iteration. Our method applies to a broad family …
Synthetic data can be used to ask more questions and accelerate discovery with provable validity guarantees.
Statistical model checking for PCTL on MDPs using reinforcement learning.
In this paper, we present multi-task structure learning for Gaussian graphical models. We analyze the sufficient number of samples for the correct recovery of the support union and edge signs. We also analyze the necessary number of samples for any conceivable method by providing information-theoretic lowe…
This work analyzes statistical properties of SAM, showing it outperforms GD.
New algorithm recovers tensor factors from incomplete measurements efficiently.
New method robust to semi-random sparse recovery, nearly-linear time.
We present a Communication-efficient Surrogate Likelihood (CSL) framework for solving distributed statistical inference problems. CSL provides a communication-efficient surrogate to the global likelihood that can be used for low-dimensional estimation, high-dimensional regularized estimation and Bayesian inference. For…
Self-training improves model accuracy by refining pseudo-labels.