Study on gradient descent in Hilbert spaces with Markov chains, focusing on mixing coefficients.
problem Analyzing convergence of gradient descent in Hilbert spaces with stationary Markov chains.
method Examined strictly stationary Markov chains with φ- and β-mixing coefficients, derived probabilistic upper bounds. result Probabilistic upper bounds on convergence behavior of gradient descent algorithm based on mixing coefficients.
Improves meta-learning efficiency with mixed-mode differentiation.
problem Efficiently calculating complex derivatives in meta-learning.
method Mixed-Flow Meta-Gradients (MixFlow-MG) for scalable differentiation.
result Significant memory and time improvements in meta-learning tasks.
GBMixed boosts mixed models for clustered data, estimating mean and variance flexibly.
problem Flexible estimation of mean and variance components in clustered data.
method Gradient Boosting framework for linear mixed models with likelihood-based gradients.
result GBMixed accurately recovers complex nonlinear fixed effects and covariances.
Gradient Boosted Mixed Models estimate mean and variance components for clustered data.
problem Limited flexibility in linear mixed models for complex settings.
method Gradient Boosting extended to mixed models with likelihood-based gradients and flexible base learners.
result Accurate recovery of variance components and improved predictive accuracy.
Improved VI method for deep mixed models in finance.
problem Inaccurate and slow variational inference in high dimensions.
method Natural gradient hybrid VI method targeting joint posterior.
result Natural gradient method is faster and more accurate than existing methods.
uHMC achieves fast mixing in high dimensions with gradient evaluations.
problem Quantifying mixing time of uHMC in high dimensions.
method Construction of successful couplings for uHMC.
result uHMC mixes in total variation with logarithmic dependence on dimension.
A new method for efficient inference in probabilistic programs with mixed support.
problem Challenges in inference for programs with both continuous and discrete latent variables.
method Stochastic gradient Markov Chain Monte Carlo algorithms.
result Outperforms existing composing inference baselines and works almost as well as inference in marginalized versions.
Gradient EM converges exponentially to optimal solution in agnostic mixtures.
problem Fitting k parametric functions to given data points without a generative model. method Gradient EM algorithm for agnostic mixtures of arbitrary parametric functions.
result Gradient EM converges exponentially to population loss minimizers with high probability.
Study on mixed Killing vector fields on Cigar Ricci-Bourguignon solitons.
problem Characterizing mixed Killing vector fields on Cigar Ricci-Bourguignon solitons.
method Analyzing the condition LVLVg=fLVg and using rigidity phenomena. result Dimension of complete mixed Killing fields is 5 and a basis is explicitly determined.
This paper resolves the Langevin Algorithm's mixing time for log-concave distributions.
problem Resolving the mixing time of the Langevin Algorithm for log-concave sampling.
method Introducing Privacy Amplification by Iteration to analyze Rényi divergence and Optimal Transport smoothing.
result Optimal mixing bounds for the Langevin Algorithm in log-concave sampling settings.
New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD.
problem Analyzing mixing times and privacy in projected Langevin algorithm and noisy SGD.
method New bounds derived using PABI framework and optimization problems.
result New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD, showing dependency on gradient regularity.
Method identifies mixed Nash equilibria in high dimensions for training mixtures of GANs.
problem Finding Nash equilibria in two-player zero-sum continuous games, especially in high dimensions.
method Parametrizing mixed strategies as mixtures of particles, updating their positions and weights using gradient descent-ascent.
result Global convergence to an approximate equilibrium for the related Langevin gradient-ascent dynamic.
Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.
problem Credit assignment issues and biased gradients in hybrid discrete-continuous action spaces.
method Mixed gradient estimator combining pathwise and score-function gradients, reformulating problems in hybrid form.
result HPO substantially outperforms PPO on inventory control and switched systems, with performance gaps increasing with continuous action dimension.
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…
Hybrid method improves sampling from multimodal distributions.
problem Sampling from multimodal posterior distributions efficiently.
method Jump-Diffusion Langevin Dynamics hybrid with Metropolis.
result Calibrated hybrid method outperforms pure methods.
Recent advances in stochastic gradient techniques have made it possible to estimate posterior distributions from large datasets via Markov Chain Monte Carlo (MCMC). However, when the target posterior is multimodal, mixing performance is often poor. This results in inadequate exploration of the posterior distribution. A…
A new method for statistical inference using SGD under φ-mixing data.
problem Valid statistical inference for time series data with general correlation.
method Proposes a mini-batch SGD estimator and associated mini-batch bootstrap procedure for φ-mixing data. result The proposed method constructs valid confidence intervals for φ-mixing data. Paper proposes a mean-field gradient descent for zero-sum games, proving convergence to Nash equilibrium.
problem Finding mixed Nash equilibria in zero-sum games with multiple players.
method Mean-field gradient descent dynamics with time-averaging, incorporating exponentially discounted gradients.
result Exponential convergence rate to mixed Nash equilibrium with respect to total variation metric.
New method for accurate Bayesian inference in GLMMs for large-scale data.
problem Challenges in scalable Bayesian inference for GLMMs due to intractable marginal likelihood and high computational cost.
method Stochastic gradient Markov Chain Monte Carlo (SGMCMC) algorithm using Fisher's identity for gradient estimation.
result Accurate posterior inference in large-sample settings with properly calibrated uncertainty.
In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics. A stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is large. The sto…
We propose a stochastic gradient Markov chain Monte Carlo (SG-MCMC) algorithm for scalable inference in mixed-membership stochastic blockmodels (MMSB). Our algorithm is based on the stochastic gradient Riemannian Langevin sampler and achieves both faster speed and higher accuracy at every iteration than the current sta…
Paper develops methods for estimating gradients of Finslerian Schrödinger equations.
problem Estimating gradients of Finslerian Schrödinger equations.
method Develops new Laplacian comparison theorem and applies it to Finslerian Schrödinger equation.
result Global and local Li-Yau type gradient estimates for positive solutions.
Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the t…
Paper tackles NAS problem by modeling it as a sparse supernet.
problem Neural Architecture Search (NAS) problem, particularly Mixed-Path Search.
method Model NAS as a sparse supernet with sparsity constraints. Use hierarchical accelerated proximal gradient algorithm for optimization.
result Proposed method finds compact, general, and powerful neural architectures.
PVI improves SIVI by directly optimizing ELBO without parametric assumptions.
problem Intractable variational densities in SIVI methods.
method Particle Variational Inference (PVI) using empirical measures to approximate optimal mixing distributions.
result PVI directly optimizes the ELBO and performs favorably compared to other SIVI methods.
Improved Metropolized HMC runtime for logconcave distributions.
problem Improving the runtime of Metropolized HMC for logconcave sampling.
method Gradient norm concentration and new mixing time analysis techniques.
result Metropolized HMC mixes in O~(κd) iterations, improving runtime by a factor of (κ/d)1/2. New method adapts to unknown mixing time in stochastic optimization.
problem Optimizing with Markovian data where mixing time is unknown.
method Combines MLMC gradient estimation with adaptive learning.
result Achieves optimal convergence rate for convex problems.
AM converges super-linearly for solving mixed linear regression problems.
problem Learning linear regressors from unlabeled observations in multiple linear regression models.
method Alternating Minimization (AM) algorithm, which alternates between label estimation and regression solving.
result AM converges super-linearly in certain parameter regimes, requiring only O(log log(1/ε)) iterations to achieve an error of ε.
Stochastic Gradient Langevin Dynamics (SGLD) is a sampling scheme for Bayesian modeling adapted to large datasets and models. SGLD relies on the injection of Gaussian Noise at each step of a Stochastic Gradient Descent (SGD) update. In this scheme, every component in the noise vector is independent and has the same sca…
Wasserstein framework solves mixed linear regression problems.
problem Mixed linear regression with multi-modal distributions.
method Wasserstein distance minimization for nonconvex-concave minimax optimization.
result WMLR achieves global convergence and generalization guarantees for two linear models.
Bayesian optimization tackles expensive discrete and mixed parameter spaces.
problem Optimizing expensive functions with discrete and mixed parameters.
method Probabilistic reparameterization to maximize expectation of AF over continuous parameters.
result Our approach provably converges to a maximizer of the AF and enjoys the same regret bounds as standard BO.
Joint sparsity offers powerful structural cues for feature selection, especially for variables that are expected to demonstrate a "grouped" behavior. Such behavior is commonly modeled via group-lasso, multitask lasso, and related methods where feature selection is effected via mixed-norms. Several mixed-norm based spar…
Enhances gradient estimates for Hermitian Monge-Ampère equations.
problem Improving estimates for Hermitian Monge-Ampère equations.
method Improves gradient estimates using Evans-Krylov and third derivatives estimates.
result Enhanced estimates for second and third order derivatives.
New Riemannian optimization improves variance estimation in mixed models.
problem Challenges in estimating variance parameters in linear mixed models due to constraints.
method Formulated as an optimization problem on a Riemannian manifold, using Riemannian gradient and Hessian.
result Yields higher quality variance parameter estimates compared to existing methods.
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 …
Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwi…
Paper studies convergence of Mean-Field GDA dynamics for MNE of continuous games.
problem Finding mixed Nash equilibria in continuous games.
method Two-scale Mean-Field Gradient Descent Ascent dynamics.
result Two-scale Mean-Field GDA converges exponentially to MNE without convexity assumptions.
Inference is typically intractable in high-treewidth undirected graphical models, making maximum likelihood learning a challenge. One way to overcome this is to restrict parameters to a tractable set, most typically the set of tree-structured parameters. This paper explores an alternative notion of a tractable set, nam…
MixMin finds optimal data mixtures for better model performance.
problem Finding the best data mixtures for improved model performance is challenging.
method Developed a gradient-based approach for optimizing a convex bi-level objective.
result MixMin mixtures uniformly improved model performance across various tasks.
New Krylov subspace methods speed up mixed-effects models with crossed random effects.
problem Slow computations for high-dimensional crossed random effects in mixed-effects models.
method Krylov subspace-based methods for generalized mixed-effects models with cross effects.
result Speedups by factors of up to 10,000 in computations for mixed-effects models.
Bayesian Bits unifies quantization and pruning through gradient optimization.
problem Joint mixed precision quantization and pruning for efficient neural networks.
method Gradient-based optimization with a novel bit width decomposition and learnable stochastic gates.
result Bayesian Bits achieves better accuracy vs. efficiency trade-off compared to static bit width networks.
The speed of convergence of the Expectation Maximization (EM) algorithm for Gaussian mixture model fitting is known to be dependent on the amount of overlap among the mixture components. In this paper, we study the impact of mixing coefficients on the convergence of EM. We show that when the mixture components exhibit …
Develops a new method for learning discrete distributions without embedding them in a continuous space.
problem Challenges in learning discrete distributions using current methodologies.
method Introduces a MAD invertible map and a mixed variational flow (MAD Mix) for discrete distributions.
result MAD Mix produces more reliable approximations than continuous-embedding flows.
Improves decentralized learning by optimizing graph mixing for data heterogeneity.
problem Data heterogeneity impacts convergence in decentralized learning, but existing methods ignore this.
method Characterized and quantified the relationship between graph mixing and data heterogeneity. Proposed an optimization approach to improve convergence.
result Our approach leads to improved test performance across various tasks.
DDICA separates nonlinear mixed signals robustly.
problem Blind source separation of nonlinear mixed signals.
method Deep deterministic neural network with matrix-based entropy function.
result DDICA effectively separates independent components with high accuracy.
AF improves classification models by adaptively weighting trees.
problem Improving classification model performance.
method AF combines OP2T for input-dependent weights and MIO for dynamic refinement.
result AF consistently outperforms RF, XGBoost, and other weighted RF.
Proposes integrating random effects into deep neural networks for better predictive performance.
problem Correlated data in real-life applications are not handled well by traditional deep neural networks.
method Uses mixed models with random effects to handle correlations in deep neural networks, minimizing Gaussian negative log-likelihood with SGD.
result Improves predictive performance over natural competitors in various correlation scenarios.
New RL method MAC improves performance in sparse reward settings.
problem Slow mixing in large state spaces or sparse rewards.
method Multi-level Monte Carlo Actor-Critic (MAC) algorithm.
result Achieves convergence rate comparable to state-of-the-art AC algorithms.