Gradient methods converge better for alternating updates in bilinear zero-sum games.
problem Understanding the dynamics of gradient algorithms for bilinear zero-sum games.
method Systematic analysis of popular gradient updates for simultaneous and alternating versions of bilinear zero-sum games.
result Alternating updates converge better than simultaneous ones, with optimal parameter setup and rates.
Paper analyzes game dynamics with negative momentum for improved stability and convergence.
problem Complexity and instability in game dynamics, especially in adversarial settings.
method Analyzed gradient-based methods with negative momentum on simple games and adversarial problems.
result Alternating gradient updates with negative momentum achieve convergence in difficult adversarial problems.
Paper proposes an algorithm to recover non-negative matrix factorization with mild conditions.
problem Understanding and guaranteeing recovery of non-negative matrix factorization.
method Alternates between updating features and decoding weights using ReLU.
result Proves recovery of ground-truth under mild conditions, including linear independence of features.
Alt-GDA outperforms Sim-GDA in minimax games with near-optimal local convergence.
problem Minimax optimization convergence rate comparison
method Alternating Gradient Descent-Ascent (Alt-GDA) vs. Simultaneous Gradient Descent-Ascent (Sim-GDA)
result Alt-GDA achieves near-optimal local convergence rate for strongly convex-strongly concave problems, while Sim-GDA converges slower.
Develops a new method for matrix factorization problems.
problem Solving a general matrix factorization model with potential function.
method Non-monotone alternating updating method based on a potential function.
result The method can outperform existing methods for specific applications.
MPI-FAUN tackles NMF for big data, offering scalable parallel algorithms.
problem Efficient parallel algorithms for NMF on big data.
method MPI-based framework for NMF, solving alternating NLS subproblems.
result Significant performance improvements over baseline implementations.
VASE uses Bayesian neural networks to improve exploration in sparse reward environments.
problem Exploration in environments with continuous control and sparse rewards.
method VASE uses a Bayesian neural network model of the environment dynamics and variational inference to alternately update the model's accuracy and policy.
result VASE outperforms other surprise-based exploration techniques in continuous control sparse reward environments.
Framework corrects noisy labels to improve DNN performance.
problem Performance degradation due to noisy labels in large-scale datasets.
method Joint optimization of DNN parameters and true labels estimation.
result Significantly outperforms state-of-the-art methods in experiments.
GAIL with neural networks converges to global optima and has a known rate.
problem Uncertainty about GAIL with neural networks achieving global optimality.
method Gradient-based alternating updates algorithm.
result Established sublinear convergence to globally optimal solution.
Improved Mondrian Forests achieve optimal rate for online classification.
problem Consistency and minimax rates for online Mondrian Forests.
method Modified Mondrian Forest algorithm with increasing lifetime parameters and alternative updating rule.
result Achieves minimax rate for Lipschitz regression function estimation.
New method detects communities in hypergraphs by embedding them into a vector space.
problem Detecting communities in hypergraphs with multi-way interactions.
method Augmenting non-uniform hypergraphs, embedding into a vector space, using an alternative updating scheme.
result Asymptotic consistencies in community detection and hypergraph estimation established.
MCFlow uses Monte Carlo sampling and flow models for imputing missing data.
problem Missing data in machine learning datasets.
method MCFlow combines normalizing flow and Monte Carlo sampling to iteratively update data imputation.
result MCFlow outperforms state-of-the-art methods in imputing data quality and semantic structure preservation.
Actor-critic converges globally in LQR with ergodic cost.
problem Theoretical understanding of actor-critic algorithm's global convergence.
method Nonasymptotic convergence analysis of actor-critic in linear quadratic regulator (LQR) setting.
result Actor-critic finds globally optimal policy and value function at a linear rate.
Proposes PredVAR model for reduced-dimensional dynamics from noisy data.
problem Extracting low-dimensional dynamics from high-dimensional noisy data.
method Probabilistic reduced-dimensional vector autoregressive model with oblique projection.
result Iterative algorithm yields dynamic latent variables with rank-ordered predictability.
Proposes GAGA algorithm for automatic hyperparameter learning in signal recovery.
problem Difficulty in selecting hyperparameters in traditional signal recovery methods.
method Global Adaptive Generative Adjustment (GAGA) algorithm for automatic hyperparameter learning and signal estimate.
result Consistency of model selection and signal estimate output.
Brain networks has attracted the interests of many neuroscientists. From functional MRI (fMRI) data, statistical tools have been developed to recover brain networks. However, the dimensionality of whole-brain fMRI, usually in hundreds of thousands, challenges the applicability of these methods. We develop a hierarchica…
A novel framework optimizes experience replay for reinforcement learning.
problem Optimizing the replay policy for better performance in off-policy reinforcement learning.
method Proposes a novel ERO framework that alternately updates the agent policy and replay policy.
result Demonstrates improved performance in various continuous control tasks.
This work presents a general framework for solving the low rank and/or sparse matrix minimization problems, which may involve multiple non-smooth terms. The Iteratively Reweighted Least Squares (IRLS) method is a fast solver, which smooths the objective function and minimizes it by alternately updating the variables an…
STORE model handles tensor responses in neuroimaging, achieving efficient and accurate estimation.
problem Handling tensor responses in neuroimaging analysis with sparse structures.
method Sparse TensOr REsponse (STORE) regression model with alternating updating algorithm.
result Established estimation error bounds and fast estimation error rates for tensor dimensions.
New method improves matrix factorization speed and accuracy.
problem Matrix factorization optimization problems suffer from biased solutions and lack of convergence guarantees.
method Proposes a novel Bregman distance for matrix factorization, enabling non-alternating schemes with convergence proof.
result Convergence to a stationary point proved for matrix factorization problems.
MissBGM uses AI and Bayesian modeling for better missing data imputation.
problem Missing data imputation in data science, especially with uncertainty quantification.
method AI-powered Bayesian generative modeling with explicit modeling of missingness mechanisms.
result MissBGM provides principled posterior uncertainty over imputations and superior performance.
Develops a regression model for partially observed dynamic tensor data.
problem Characterizing the relationship between dynamic tensor data and external covariates when data is only partially observed.
method Introduces low-rank, sparsity, and fusion structures on the regression coefficient tensor, and uses a loss function projected over observed entries. Developed an efficient non-convex alternating updating algorithm.
result Derived finite-sample error bounds for the estimator.
AutoLoss learns optimal schedules for alternating optimization tasks.
problem Optimizing different task objectives with alternating updates.
method Meta-learning framework to learn and determine the optimization schedule.
result AutoLoss improves convergence quality on multiple ML tasks.
Paper proposes a deep subspace clustering method using multi-level representations.
problem Deep subspace clustering of images.
method Convolutional autoencoders with multiple fully-connected layers for multi-level representations, loss minimization with iterative updates.
result The method outperforms state-of-the-art methods on real-world datasets.
New algorithm tackles low-rank constraints in optimal transport problems.
problem Optimal transport problems with low-rank constraints.
method Explicit factorization of low-rank couplings as a product of sub-coupling factors linked by a common marginal.
result Stationary convergence of the algorithm proved.
A new policy improvement method using CEM for Actor-Critic.
problem Improving policy efficiency and robustness in reinforcement learning.
method Greedy Actor-Critic (Greedy AC) using Conditional Cross-Entropy Method (CCEM).
result Greedy AC outperforms Soft Actor-Critic and is less sensitive to entropy regularization.
A method improves Cryo-EM 3D map refinement by regularizing rotation estimation.
problem Noise-robustness vs. data-consistency in Cryo-EM 3D map reconstruction.
method Ellipsoidal support lifting (ESL) for regularizing and approximating the global minimizer over Riemannian manifolds.
result The induced bias due to regularizing effect of ESL estimates better rotations than global optimisation.
L2SC improves spectral clustering performance by selectively transferring knowledge across tasks.
problem L2SC tackles the challenge of incorporating new spectral clustering tasks without relearning all previous tasks.
method L2SC uses an orthogonal basis library and feature embedding library to selectively transfer knowledge from previously learned tasks to new tasks.
result L2SC outperforms state-of-the-art spectral clustering algorithms on real-world benchmark datasets.
Develops new reinforcement learning methods for complex constrained decision-making problems.
problem Complex constrained decision-making problems with a continuum of constraints.
method Proposes semi-infinitely constrained Markov decision processes (SICMDPs) and two reinforcement learning algorithms: SI-CRL and SI-CPO.
result Demonstrates the effectiveness of SI-CRL and SI-CPO in solving complex sequential decision-making tasks.
NAS improves gliomas segmentation on MRI scans.
problem Designing optimal deep learning architectures for brain tumor segmentation.
method Neural architecture search with probabilistic parameter learning for MRI brain tumor segmentation.
result Two optimal neural architectures for brain tumor segmentation were discovered.
Algorithm recovers factors of rank-1 matrices from noisy measurements.
problem Estimating factors of a rank-1 matrix from nonlinearly transformed and noisy measurements.
method Alternating minimization with random initialization and analysis of empirical error recursion.
result Algorithm converges geometrically fast from random initialization, with sharp guarantees.
This work generates training-time adversarial data using auto-encoders to manipulate classifiers.
problem Manipulating the behavior of trained classifiers during test time with bounded perturbation.
method An auto-encoder-like network generates perturbations, learning to update weights to produce harmful noise.
result The method can manipulate classifiers effectively, showing good transferability.
NoFAS combines variational inference and adaptive surrogate models for efficient inference of computationally expensive models.
problem Efficient inference of parameters from data with computationally expensive models.
method Variational inference with normalizing flow and adaptive surrogate model training.
result NoFAS reduces computational cost without sacrificing inferential accuracy.
Sharp convergence analysis for nonconvex regression models.
problem Nonconvex optimization in regression models with normally distributed covariates.
method Gaussian comparison theorems for analyzing iterative algorithms.
result Sharp global convergence rates for various statistical models.
APGD algorithm efficiently recovers over-parameterized matrices from noisy measurements.
problem Matrix sensing problem with over-parameterization and noisy measurements.
method Alternating preconditioned gradient descent (APGD) algorithm incorporating preconditioning terms.
result APGD converges to a near-optimal error at a linear rate.