arXiv research

Paper extends nonparametric regression bounds for dependent $\beta$-mixing samples.

New RL theory reduces sample complexity for mixing MDPs.

MALA mixes efficiently under smoothness and isoperimetry assumptions.

We study the problem of semi-supervised singing voice separation, in which the training data contains a set of samples of mixed music (singing and instrumental) and an unmatched set of instrumental music. Our solution employs a single mapping function g, which, applied to a mixed sample, recovers the underlying instrum…

Study shows DQN's performance degrades with temporal dependence in data.

SelectMix improves deep learning robustness against noisy labels.

New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.

This paper resolves the Langevin Algorithm's mixing time for log-concave distributions.

New algorithm improves mixing in Bayesian mixture models.

MALA mixes optimally in κ√d steps for log-concave sampling.

Paper analyzes Nyström regularization for time series forecasting with sequential sub-sampling.

The literature on statistical learning for time series assumes the asymptotic independence or ``mixing' of the data-generating process. These mixing assumptions are never tested, nor are there methods for estimating mixing rates from data. We give an estimator for the $β$-mixing rate based on a single stationary sample…

PatchUp improves CNN robustness with mixed feature blocks.

Overfitting & underfitting and stable training are an important challenges in machine learning. Current approaches for these issues are mixup, SamplePairing and BC learning. In our work, we state the hypothesis that mixing many images together can be more effective than just two. Batchboost pipeline has three stages: (…

Mix-IRLS solves imbalanced mixed linear regression problems efficiently.

Deep neuroevolution, that is evolutionary policy search methods based on deep neural networks, have recently emerged as a competitor to deep reinforcement learning algorithms due to their better parallelization capabilities. However, these methods still suffer from a far worse sample efficiency. In this paper we invest…

New method improves sampling from logconcave distributions truncated on polytopes.

Method completes mixed matrix from complex surveys with heterogeneous missingness.

Paper improves generalization bounds for multi-kernel learning with mixed datasets.

New algorithm for sampling from distributions with thin tails.

We study probability measures induced by set functions with constraints. Such measures arise in a variety of real-world settings, where prior knowledge, resource limitations, or other pragmatic considerations impose constraints. We consider the task of rapidly sampling from such constrained measures, and develop fast M…

Study nearest-neighbor radii under dependent sampling, finding they remain informative.

DiGS improves sampling from multi-modal distributions.

Markov chain Monte Carlo (MCMC) algorithms are simple and extremely powerful techniques to sample from almost arbitrary distributions. The flaw in practice is that it can take a large and/or unknown amount of time to converge to the stationary distribution. This paper gives sufficient conditions to guarantee that univa…

SBMs learn manifold-like structures by mixing samples with a non-conservative field.

Paper analyzes agnostic learning of mixed linear regression without generative models.

The optimization of expensive to evaluate, black-box, mixed-variable functions, i.e. functions that have continuous and discrete inputs, is a difficult and yet pervasive problem in science and engineering. In Bayesian optimization (BO), special cases of this problem that consider fully continuous or fully discrete doma…

This paper focuses on learning rate analysis of distributed kernel ridge regression for strong mixing sequences. Using a recently developed integral operator approach and a classical covariance inequality for Banach-valued strong mixing sequences, we succeed in deriving optimal learning rate for distributed kernel ridg…

We propose and analyze two new MCMC sampling algorithms, the Vaidya walk and the John walk, for generating samples from the uniform distribution over a polytope. Both random walks are sampling algorithms derived from interior point methods. The former is based on volumetric-logarithmic barrier introduced by Vaidya wher…

Study on sparse recovery with mixed-quality data, establishing sample-size conditions.

In this paper we address the following question: Can we approximately sample from a Bayesian posterior distribution if we are only allowed to touch a small mini-batch of data-items for every sample we generate?. An algorithm based on the Langevin equation with stochastic gradients (SGLD) was previously proposed to solv…

Paper proposes a method to improve MCMC sampling for energy-based models.

A new sampling method for log-concave distributions with warm starts and barriers.

Lower bound on BART's mixing time increases with data points.

We develop algorithms to learn non-linear dynamical systems without mixing assumptions.

Hybrid method improves sampling from multimodal distributions.

We consider the problem of solving mixed random linear equations with $k$ components. This is the noiseless setting of mixed linear regression. The goal is to estimate multiple linear models from mixed samples in the case where the labels (which sample corresponds to which model) are not observed. We give a tractable a…

GP-MRO discovers robust mixed strategies for unknown objectives.

Proposes meTS for efficient exploration in correlated bandits.

Aioli unifies language model data mixing methods and improves performance.

This article provides the first procedure for computing a fully data-dependent interval that traps the mixing time $t_{\text{mix}}$ of a finite reversible ergodic Markov chain at a prescribed confidence level. The interval is computed from a single finite-length sample path from the Markov chain, and does not require t…

We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require …

DMIDAS improves long-term forecasting accuracy in healthcare and electricity data.

We study the problem of sampling from the power posterior distribution in Bayesian Gaussian mixture models, a robust version of the classical posterior. This power posterior is known to be non-log-concave and multi-modal, which leads to exponential mixing times for some standard MCMC algorithms. We introduce and study …

Develops a new method for learning discrete distributions without embedding them in a continuous space.

Mixed membership factorization is a popular approach for analyzing data sets that have within-sample heterogeneity. In recent years, several algorithms have been developed for mixed membership matrix factorization, but they only guarantee estimates from a local optimum. Here, we derive a global optimization (GOP) algor…

New bounds for SMC show its advantage over MCMC in multimodal distributions.

Inference in general Ising models is difficult, due to high treewidth making tree-based algorithms intractable. Moreover, when interactions are strong, Gibbs sampling may take exponential time to converge to the stationary distribution. We present an algorithm to project Ising model parameters onto a parameter set that…