arXiv research

Framework improves gradient estimation for faster training convergence.

The clustering algorithms that view each object data as a single sample drawn from a certain distribution, Gaussian distribution, for example, has been a hot topic for decades. Many clustering algorithms: such as k-means and spectral clustering are proposed based on the single sample assumption. However, in real life, …

Paper finds efficient OPE estimator for multiple logging policies with minimum variance.

MT-SGD samples from multiple target distributions using gradient descent.

Matrix multiplication is a fundamental building block for large scale computations arising in various applications, including machine learning. There has been significant recent interest in using coding to speed up distributed matrix multiplication, that are robust to stragglers (i.e., machines that may perform slower …

New method combines multiple data sources for optimal decision-making with limited outcomes.

We determine the sample complexity of pure exploration bandit problems with multiple good answers. We derive a lower bound using a new game equilibrium argument. We show how continuity and convexity properties of single-answer problems ensures that the Track-and-Stop algorithm has asymptotically optimal sample complexi…

This paper solves the multiple reference model problem in RLHF with exact solutions and sample complexity guarantees.

We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared with grid sampling and uniform sampling techniques, it achieves higher generalization performance. We validate the strategy on two artificial…

Improved locally private sparse estimation with multiple samples per user.

We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple experiments, and their related data distributions. Each collected sample is associat…

Proposes using Wasserstein barycenters for robust optimization with multiple data sources.

Improved SVMs learn from few samples with composition and multiple scales.

SMTM improves MCMC sampling in high dimensions with multiple proposals and stereographic integration.

Study reduces NAS search cost by generating multiple complex architectures in one shot.

Shielded LMC samples from non-convex spaces with repulsive drift.

We propose a new sampling-based approach for approximate inference in filtering problems. Instead of approximating conditional distributions with a finite set of states, as done in particle filters, our approach approximates the distribution with a weighted sum of functions from a set of continuous functions. Central t…

Introduces Rashomon Capacity to measure predictive multiplicity in probabilistic classifiers.

We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is done without using matching or parallel data, i.e., without samples of the same …

Enhances anomaly detection using multiple reference datasets.

Enhanced feedback model improves sample-efficiency in POMDPs.

We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the…

Localized sketching improves matrix multiplication and ridge regression complexity.

Paper settles sample complexity for learning from multiple distributions.

WiGS improves active learning for regression by dynamically selecting informative samples.

Given samples from a distribution, how many new elements should we expect to find if we continue sampling this distribution? This is an important and actively studied problem, with many applications ranging from unseen species estimation to genomics. We generalize this extrapolation and related unseen estimation proble…

Bayesian methods improve tracking multiple objects through dynamic dependencies.

Unified framework for simulation-based inference learns a single model for multiple tasks.

We describe the first sub-quadratic sampling algorithm for the Multiplicative Attribute Graph Model (MAGM) of Kim and Leskovec (2010). We exploit the close connection between MAGM and the Kronecker Product Graph Model (KPGM) of Leskovec et al. (2010), and show that to sample a graph from a MAGM it suffices to sample sm…

Advances in molecular "omics'" technologies have motivated new methodology for the integration of multiple sources of high-content biomedical data. However, most statistical methods for integrating multiple data matrices only consider data shared vertically (one cohort on multiple platforms) or horizontally (different …

A new bandit algorithm for web page item display.

Researchers study fairness-accuracy tradeoffs in predictive models for multiple groups.

A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However, the existing complementary-label learning methods cannot learn from the easily …

LLM-as-a-service prices vary arbitrarily due to tokenization multiplicity.

Neural Architecture Search (NAS) has shown great potentials in finding better neural network designs. Sample-based NAS is the most reliable approach which aims at exploring the search space and evaluating the most promising architectures. However, it is computationally very costly. As a remedy, the one-shot approach ha…

Measures consistency of tabular LLM predictions under fine-tuning multiplicity.

We propose a Genetic Programming architecture for the generation of foreign exchange trading strategies. The system's principal features are the evolution of free-form strategies which do not rely on any prior models and the utilization of price series from multiple instruments as input data. This latter feature consti…

Introduces MLM dataset for multitask learning across multiple languages and modalities.

This paper studies the sample complexity of searching over multiple populations. We consider a large number of populations, each corresponding to either distribution P0 or P1. The goal of the search problem studied here is to find one population corresponding to distribution P1 with as few samples as possible. The main…

Proposes a robust FMR model for handling sample heterogeneity.

Algorithm identifies Pareto front using multiple context directions and reuses exploration samples.

We study binary classification in the setting where the learner is presented with multiple corrupted training samples, with possibly different sample sizes and degrees of corruption, and introduce an approach based on minimizing a weighted combination of corruption-corrected empirical risks. We establish a generalizati…

In the mixture models problem it is assumed that there are $K$ distributions $θ_{1},\ldots,θ_{K}$ and one gets to observe a sample from a mixture of these distributions with unknown coefficients. The goal is to associate instances with their generating distributions, or to identify the parameters of the hidden distribu…

We learn linear models from nonlinear systems using multiple trajectories and regularization.

Study tackles RLHF with diverse human feedback, showing limitations and proposing a meta-learning approach.

The paper develops methods to identify stable associations across multiple studies.

PBO framework optimizes latent preferences over multiple objectives.

Study learns dynamics of linear systems from multiple short trajectories.