arXiv research

DSPI connects natural policy gradient to policy iteration, proving global convergence.

WaveFit uses fixed-point iteration to create high-quality neural vocoders.

Unified framework for AMP iterations using graph indexing.

Machine learning (ML) training algorithms often possess an inherent self-correcting behavior due to their iterative-convergent nature. Recent systems exploit this property to achieve adaptability and efficiency in unreliable computing environments by relaxing the consistency of execution and allowing calculation errors…

OMWU shows last iterate convergence in convex-concave games.

A novel framework refines diffusion models iteratively for better downstream reward optimization.

A framework for discrete structure recovery using iterative algorithms.

Establishes geometric convergence of iterative optimization algorithms.

Extends JKO scheme for iterative algorithms with unknown parameters.

Combines soft greediness with Modified Policy Iteration for more efficient deep reinforcement learning.

New algorithm solves minimax games with linear constraints.

HyperImpute improves iterative imputation by automatically selecting models and hyperparameters.

Iterative method learns unknown constraints for MPC control.

A new framework for selecting base classes in multi-class classification boosts accuracy.

We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint or penalization is considered, and generalization is achieved by (early) stoppin…

Exchangeable graphs arise via a sampling procedure from measurable functions known as graphons. A natural estimation problem is how well we can recover a graphon given a single graph sampled from it. One general framework for estimating a graphon uses step-functions obtained by partitioning the nodes of the graph accor…

A new hybrid framework reduces quantum runtime and noise effects.

In today's data driven world, storing, processing, and gleaning insights from large-scale data are major challenges. Data compression is often required in order to store large amounts of high-dimensional data, and thus, efficient inference methods for analyzing compressed data are necessary. Building on a recently desi…

ADS explains object differences by quantifying and removing underlying properties.

The paper analyzes SW-SGD for MSE in biased and variance-reduced gradient estimators.

This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…

Theoretical model for iterative user discovery in recommender systems.

Improved iterative hard thresholding for faster, sparser solutions.

Exponential distribution is ubiquitous in the framework of multi-agent systems. An alternative approach with an economic motivation to derive the exponential distribution in the framework of iterations in the space of distributions is disclosed.

Privacy amplification improved through contraction coefficients and $E_γ$-divergence.

We provide a new theoretical analysis framework to investigate online gradient descent in the dynamic environment. Comparing with the previous work, the new framework recovers the state-of-the-art dynamic regret, but does not require extra gradient queries for every iteration. Specifically, when functions are $α$ stron…

New framework predicts AMP behavior in spiked models for finite iterations.

Paper proposes a novel method to reduce mutual information for missing data imputation.

New framework for probabilistic linear solvers reduces manual effort.

Enhances privacy in machine learning through Rényi Pufferfish mechanisms.

We present RandomizedCCA, a randomized algorithm for computing canonical analysis, suitable for large datasets stored either out of core or on a distributed file system. Accurate results can be obtained in as few as two data passes, which is relevant for distributed processing frameworks in which iteration is expensive…

Unified framework for analyzing convergence of RSAs using Wasserstein divergence.

Faster WIND accelerates iterative BOND for LLM alignment.

AI-driven framework optimizes MCMC-based preconditioners for faster linear system solving.

RL accelerates portfolio optimization and option pricing by dynamically adjusting preconditioner sizes.

Adaptive SAA solves large-scale stochastic linear programs efficiently.

Given a graph where every node has certain attributes associated with it and some nodes have labels associated with them, Collective Classification (CC) is the task of assigning labels to every unlabeled node using information from the node as well as its neighbors. It is often the case that a node is not only influenc…

OptEx accelerates first-order optimization with parallelized iterations.

Exponential distribution is ubiquitous in the framework of multi-agent systems. Usually, it appears as an equilibrium state in the asymptotic time evolution of statistical systems. It has been explained from very different perspectives. In statistical physics, it is obtained from the principle of maximum entropy. In th…

We introduce and analyze stochastic optimization methods where the input to each gradient update is perturbed by bounded noise. We show that this framework forms the basis of a unified approach to analyze asynchronous implementations of stochastic optimization algorithms.In this framework, asynchronous stochastic optim…

Paper characterizes gradient descent in high-dimensional learning problems.

This dissertation advances scalable Gaussian processes using iterative methods and pathwise conditioning.

A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce…

Recursive stochastic algorithms have gained significant attention in the recent past due to data driven applications. Examples include stochastic gradient descent for solving large-scale optimization problems and empirical dynamic programming algorithms for solving Markov decision problems. These recursive stochastic a…

Unified reinforcement learning methods using hybrid inference.

In many distributed learning problems, the heterogeneous loading of computing machines may harm the overall performance of synchronous strategies. In this paper, we propose an effective asynchronous distributed framework for the minimization of a sum of smooth functions, where each machine performs iterations in parall…

A new method to prune neural networks with iterative randomization improves efficiency.

New inequalities help optimize first-order algorithms for statistical risk analysis.