arXiv research

OPT framework improves neural network generalization by learning an orthogonal transformation.

This paper compares two methods for training neural ODEs in time-series regression and CNFs.

A new method for efficient optimal partial transport in 1D.

New research shows logistic regression can achieve optimal error rate for agnostic learning of halfspaces.

Deep RL learns 2-opt heuristics to improve TSP solutions.

Improved bounds for continuous functions in online learning.

Adversarial training improves robustness of halfspaces in noisy data.

The paper analyzes online learning of smooth functions in both single and multi-variable settings.

Non-convex SGD learns halfspaces with adversarial label noise efficiently.

The paper proves a margin inequality for separating hyperplanes, useful for analyzing algorithmic bias.

The study bounds errors in learning smooth functions online.

The distributional perspective on reinforcement learning (RL) has given rise to a series of successful Q-learning algorithms, resulting in state-of-the-art performance in arcade game environments. However, it has not yet been analyzed how these findings from a discrete setting translate to complex practical application…

Efficiently optimize GPs by reusing candidate solutions multiple times.

HF-opt uses Hamiltonian dynamics to optimize functions, achieving accelerated rates with randomized integration time.

Paper introduces non-linearity signature to measure deep neural network performance.

New tool for parallel and private stochastic convex optimization reduces query complexity.

The study establishes SQ lower bounds for learning halfspaces and ReLUs under Gaussian marginals.

Designs efficient algorithms to maximize the expectation of Gaussian random variables.

Given a subset S of vertices of an undirected graph G, the cut-improvement problem asks us to find a subset S that is similar to A but has smaller conductance. A very elegant algorithm for this problem has been given by Andersen and Lang [AL08] and requires solving a small number of single-commodity maximum flow comput…

Large language models predict stock market returns better than traditional methods.

Recently, neural networks trained as optimizers under the "learning to learn" or meta-learning framework have been shown to be effective for a broad range of optimization tasks including derivative-free black-box function optimization. Recurrent neural networks (RNNs) trained to optimize a diverse set of synthetic non-…

Study on random linear programs and their connection to mean widths of random polyhedrons.

We consider the problem of computing the best-fitting ReLU with respect to square-loss on a training set when the examples have been drawn according to a spherical Gaussian distribution (the labels can be arbitrary). Let $\mathsf{opt} < 1$ be the population loss of the best-fitting ReLU. We prove: 1. Finding a ReLU wit…

Gradient descent learns a single neuron without knowing the relationship between inputs and labels.

In this paper, we propose scalable methods for maximizing a regularized submodular function $f = g - \ell$ expressed as the difference between a monotone submodular function $g$ and a modular function $\ell$. Indeed, submodularity is inherently related to the notions of diversity, coverage, and representativeness. In p…

Near-optimal SQ hardness shows learning halfspaces with Massart noise is hard.

A collection of the accepted abstracts for the Machine Learning for Health (ML4H) workshop at NeurIPS 2019. This index is not complete, as some accepted abstracts chose to opt-out of inclusion.

Bayesian Neural Networks detect gravitational wave events with high accuracy and real-time potential.

Optimizes state monitoring in Markovian systems with cost constraints.

Hardness proof for agnostically learning halfspaces from worst-case lattice problems.

We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited model queries are allowed and only the decision is provided to a queried data input. Several algori…

We study distributed computing of the truncated singular value decomposition problem. We develop an algorithm that we call \texttt{LocalPower} for improving communication efficiency. Specifically, we uniformly partition the dataset among $m$ nodes and alternate between multiple (precisely $p$) local power iterations an…

Polynomial-time algorithm for learning halfspaces with Gaussian-distributed data and adversarial noise.

Gradient descent finds halfspaces with low error for agnostic learning.

The ubiquitous use of machine learning algorithms brings new challenges to traditional database problems such as incremental view update. Much effort is being put in better understanding and debugging machine learning models, as well as in identifying and repairing errors in training datasets. Our focus is on how to as…

New method achieves small-loss regret bounds in random-order model.

We analyze optimal weighted ridge regression in overparameterized linear models.

The paper mentioned in the title introduces the entropic value at risk. I give some extra comments and using the general theory make a relation with some commonotone risk measures.

Opt-BBAI identifies the best arm with minimal batches and pulls, optimizing both sample and batch complexity.

Efficient algorithm for learning halfspaces in a new model with polynomial time complexity.

A deep learning model predicts future cache accesses with high accuracy.

Item recommendation is the task of predicting a personalized ranking on a set of items (e.g. websites, movies, products). In this paper, we investigate the most common scenario with implicit feedback (e.g. clicks, purchases). There are many methods for item recommendation from implicit feedback like matrix factorizatio…

We study the problem of {\em properly} learning large margin halfspaces in the agnostic PAC model. In more detail, we study the complexity of properly learning $d$-dimensional halfspaces on the unit ball within misclassification error $α\cdot \mathrm{OPT}_γ + ε$, where $\mathrm{OPT}_γ$ is the optimal $γ$-margin error r…

A new EM algorithm improves inference from large datasets.

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length o…

Optimal weighted random forests improve prediction accuracy.

FedPower improves eigenspace estimation privacy in federated learning.

Optimized GPRNN reduces model complexity and overfitting, improving performance.