Search Results for author:
Found 64 papers, 11 papers with code
Online EM Algorithm for Latent Data Models
The resulting algorithm is usually simpler and is shown to achieve convergence to the stationary points of the Kullback-Leibler divergence between the marginal distribution of the observation and the model distribution at the optimal rate, i. e., that of the maximum likelihood estimator.
Kernel Change-point Analysis
Change-point analysis of an (unlabelled) sample of observations consists in, first, testing whether a change in the distribution occurs within the sample, and second, if a change occurs, estimating the change-point instant after which the distribution of the observations switches from one distribution to another different distribution.
Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning
We consider the minimization of a convex objective function defined on a Hilbert space, which is only available through unbiased estimates of its gradients.
Adaptive parallel tempering algorithm
Parallel tempering is a generic Markov chain Monte Carlo sampling method which allows good mixing with multimodal target distributions, where conventional Metropolis-Hastings algorithms often fail.
Computation
Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)
We consider the stochastic approximation problem where a convex function has to be minimized, given only the knowledge of unbiased estimates of its gradients at certain points, a framework which includes machine learning methods based on the minimization of the empirical risk.
Adaptive Multinomial Matrix Completion
The task of estimating a matrix given a sample of observed entries is known as the \emph{matrix completion problem}.
Probabilistic low-rank matrix completion on finite alphabets
The task of reconstructing a matrix given a sample of observedentries is known as the matrix completion problem.
On the Online Frank-Wolfe Algorithms for Convex and Non-convex Optimizations
With a strongly convex stochastic cost and when the optimal solution lies in the interior of the constraint set or the constraint set is a polytope, the regret bound and anytime optimality are shown to be ${\cal O}( \log^3 T / T )$ and ${\cal O}( \log^2 T / T)$, respectively, where $T$ is the number of rounds played.
High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm
We consider in this paper the problem of sampling a high-dimensional probability distribution $\pi$ having a density with respect to the Lebesgue measure on $\mathbb{R}^d$, known up to a normalization constant $x \mapsto \pi(x)= \mathrm{e}^{-U(x)}/\int_{\mathbb{R}^d} \mathrm{e}^{-U(y)} \mathrm{d} y$.
Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo
We illustrate our framework on the popular Stochastic Gradient Langevin Dynamics (SGLD) algorithm and propose a novel SG-MCMC algorithm referred to as Stochastic Gradient Richardson-Romberg Langevin Dynamics (SGRRLD).
Decentralized Frank-Wolfe Algorithm for Convex and Non-convex Problems
The convergence of the proposed algorithm is studied by viewing the decentralized algorithm as an inexact FW algorithm.
The promises and pitfalls of Stochastic Gradient Langevin Dynamics
As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target posterior and behaves like Stochastic Gradient Descent (SGD).
Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
We illustrate these settings with the online EM algorithm and the policy-gradient method for average reward maximization in reinforcement learning.
On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
To alleviate this problem, Neal and Hinton have proposed an incremental version of the EM (iEM) in which at each iteration the conditional expectation of the latent data (E-step) is updated only for a mini-batch of observations.
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise
Our bounds show that there is no discrepancy in the convergence rate between Markovian and martingale noise, only the constants are affected by the mixing time of the Markov chain.
MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC).
Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization
The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting.
A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm
The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations.
A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm
The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations.
Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees
This paper fills the gap by developing general tools to ensure that a class of nonreversible Markov kernels, possibly relying on complex transforms, has the desired invariance property and leads to convergent algorithms.
MISSO: Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex and Nonsmooth Problems
Many constrained, nonconvex and nonsmooth optimization problems can be tackled using the majorization-minimization (MM) method which alternates between constructing a surrogate function which upper bounds the objective function, and then minimizing this surrogate.
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain.
Rates of convergence for density estimation with generative adversarial networks
In this work we undertake a thorough study of the non-asymptotic properties of the vanilla generative adversarial networks (GANs).
NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant Z are challenging problems.
$\texttt{DoStoVoQ}$: Doubly Stochastic Voronoi Vector Quantization SGD for Federated Learning
The growing size of models and datasets have made distributed implementation of stochastic gradient descent (SGD) an active field of research.
The Perturbed Prox-Preconditioned SPIDER algorithm for EM-based large scale learning
Incremental Expectation Maximization (EM) algorithms were introduced to design EM for the large scale learning framework by avoiding the full data set to be processed at each iteration.
QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
The objective of Federated Learning (FL) is to perform statistical inference for data which are decentralised and stored locally on networked clients.
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system $\bar{A}\theta = \bar{b}$ for which $\bar{A}$ and $\bar{b}$ can only be accessed through random estimates $\{({\bf A}_n, {\bf b}_n): n \in \mathbb{N}^*\}$.
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
Performing reliable Bayesian inference on a big data scale is becoming a keystone in the modern era of machine learning.
Monte Carlo Variational Auto-Encoders
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO).
Federated Expectation Maximization with heterogeneity mitigation and variance reduction
The Expectation Maximization (EM) algorithm is the default algorithm for inference in latent variable models.
Local-Global MCMC kernels: the best of both worlds
Recent works leveraging learning to enhance sampling have shown promising results, in particular by designing effective non-local moves and global proposals.
NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform
Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant $\mathrm{Z}$ are challenging problems.
Federated-EM with heterogeneity mitigation and variance reduction
The Expectation Maximization (EM) algorithm is the default algorithm for inference in latent variable models.
Diffusion bridges vector quantized Variational AutoEncoders
In this work, we propose a new model to train the prior and the encoder/decoder networks simultaneously.
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
We propose the Bayes-UCBVI algorithm for reinforcement learning in tabular, stage-dependent, episodic Markov decision process: a natural extension of the Bayes-UCB algorithm by Kaufmann et al. (2012) for multi-armed bandits.
FedPop: A Bayesian Approach for Personalised Federated Learning
We provide non-asymptotic convergence guarantees for the proposed algorithms and illustrate their performances on various personalised federated learning tasks.
Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study
This paper studies the Variational Inference (VI) used for training Bayesian Neural Networks (BNN) in the overparameterized regime, i. e., when the number of neurons tends to infinity.
Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation
Our finite-time instance-dependent bounds for the averaged LSA iterates are sharp in the sense that the leading term we obtain coincides with the local asymptotic minimax limit.
BR-SNIS: Bias Reduced Self-Normalized Importance Sampling
This method is a wrapper in the sense that it uses the same proposal samples and importance weights as SNIS, but makes clever use of iterated sampling--importance resampling (ISIR) to form a bias-reduced version of the estimator.
Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees
We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon $H$ with $S$ states, and $A$ actions.
Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms
This paper focuses on Bayesian inference in a federated learning context (FL).
AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks
First, we formulate the training of quantized neural networks (QNNs) as a smoothed sequence of interval-constrained optimization problems.
Stochastic Variable Metric Proximal Gradient with variance reduction for non-convex composite optimization
This paper introduces a novel algorithm, the Perturbed Proximal Preconditioned SPIDER algorithm (3P-SPIDER), designed to solve finite sum non-convex composite optimization.
State and parameter learning with PaRIS particle Gibbs
The particle-based, rapid incremental smoother PaRIS is a sequential Monte Carlo (SMC) technique allowing for efficient online approximation of expectations of additive functionals under the smoothing distribution in these models.
Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning
Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity to deal with a large amount of data observed with uncertainties.
Rosenthal-type inequalities for linear statistics of Markov chains
In this paper, we establish novel deviation bounds for additive functionals of geometrically ergodic Markov chains similar to Rosenthal and Bernstein inequalities for sums of independent random variables.
Fast Rates for Maximum Entropy Exploration
Finally, we apply developed regularization techniques to reduce sample complexity of visitation entropy maximization to $\widetilde{\mathcal{O}}(H^2SA/\varepsilon^2)$, yielding a statistical separation between maximum entropy exploration and reward-free exploration.
Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold
We consider the problem of minimizing a non-convex function over a smooth manifold $\mathcal{M}$.
Restarted Bayesian Online Change-point Detection for Non-Stationary Markov Decision Processes
We consider the problem of learning in a non-stationary reinforcement learning (RL) environment, where the setting can be fully described by a piecewise stationary discrete-time Markov decision process (MDP).
One-Step Distributional Reinforcement Learning
Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return.
Distributional Reinforcement Learning
reinforcement-learning
+1
FAVANO: Federated AVeraging with Asynchronous NOdes
In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments.
First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
We present a unified approach for the theoretical analysis of first-order gradient methods for stochastic optimization and variational inequalities.
Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized.
Monte Carlo guided Diffusion for Bayesian linear inverse problems
Ill-posed linear inverse problems arise frequently in various applications, from computational photography to medical imaging.
Deep Reinforcement Learning Algorithms for Hybrid V2X Communication: A Benchmarking Study
In today's era, autonomous vehicles demand a safety level on par with aircraft.
Finite-Sample Analysis of the Temporal Difference Learning
In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear functional approximation for policy evaluation in discounted Markov Decision Processes.
Demonstration-Regularized RL
In particular, we study the demonstration-regularized reinforcement learning that leverages the expert demonstrations by KL-regularization for a policy learned by behavior cloning.
Bayesian ECG reconstruction using denoising diffusion generative models
In this work, we propose a denoising diffusion generative model (DDGM) trained with healthy electrocardiogram (ECG) data that focuses on ECG morphology and inter-lead dependence.
Efficient Conformal Prediction under Data Heterogeneity
Conformal Prediction (CP) stands out as a robust framework for uncertainty quantification, which is crucial for ensuring the reliability of predictions.
SCAFFLSA: Quantifying and Eliminating Heterogeneity Bias in Federated Linear Stochastic Approximation and Temporal Difference Learning
In this paper, we perform a non-asymptotic analysis of the federated linear stochastic approximation (FedLSA) algorithm.
Incentivized Learning in Principal-Agent Bandit Games
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent.
Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
In this work, we take a different approach and utilize the specific structure of the DDM prior to define a set of intermediate and simpler posterior sampling problems, resulting in a lower approximation error compared to previous methods.
Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations
Can the parameters of a hidden Markov model (HMM) be estimated from a single sweep through the observations -- and additionally, without being trapped at a local optimum in the likelihood surface?
