Proposes m-POT to improve m-OT's misspecified mappings issue.
problem Misspecified mappings in mini-batch optimal transport.
method Partial optimal transport (POT) between mini-batch empirical measures.
result m-POT alleviates incorrect mappings compared to current methods.
A new method for mini-batch optimal transport improves scalability and accuracy.
problem Desired estimation and proper metric approximation in m-OT.
method BoMb-OT: Finds optimal coupling between mini-batches.
result BoMb-OT approximates a proper metric and improves m-OT's performance.
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance define…
Proposes ESCFR to estimate treatment effects from biased data.
problem Treatment selection bias in observational data.
method Stochastic optimal transport with relaxed mass-preserving and proximal factual outcome regularizers.
result Significantly better performance in estimating treatment effects.
Improved neural framework for scaling entropic MOT with significant computational gains.
problem High computational overhead in multimarginal optimal transport.
method Neural Entropic MOT (NEMOT) using mini-batch training to reduce complexity.
result Significant speedups and feasibility improvements for multimarginal data.
A mesh-free method solves continuum-marginal optimal transport problems.
problem Recovering minimum-energy velocity fields from time-continuous probability marginals.
method Embeds weak continuity equation in a reproducing kernel Hilbert space, optimizing with mini-batch stochastic methods.
result Accurately recovers drift and maintains marginal consistency in synthetic experiments.
CT-OT Flow estimates continuous-time dynamics from discrete snapshots.
problem Estimating continuous-time dynamics from temporally aggregated snapshots with noisy or uncertain timestamps.
method Two-stage framework: aligning neighboring intervals via partial optimal transport (POT) and reconstructing a continuous-time distribution through temporal kernel smoothing.
result Reduces distributional and trajectory errors compared with existing methods across synthetic and real datasets.
New method for scalable barycenter computation using Wasserstein gradient flows.
problem Scalability and integration of label information in barycenter computation.
method Gradient flows in Wasserstein space, time discretization, mini-batch optimal transport, modular regularization, task-aware functions, supervised information integration.
result Empirically validated new state-of-the-art barycenter solver with labeled barycenters outperforming unlabeled ones.
AlignFlow improves FGMs by optimizing noise and data alignment.
problem Optimal Transport methods for FGMs are limited by scalability issues.
method Introduces Semi-Discrete Optimal Transport (SDOT) to enhance FGM training.
result AlignFlow scales well to large datasets and model architectures.
Efficiently predicts optimal transport plans using sliced potentials.
problem Predicting optimal transport plans across multiple measure pairs efficiently.
method Regression-based and objective-based amortization strategies using sliced optimal transport potentials.
result Efficient and accurate prediction of optimal transport plans for various tasks.
DEOT method compares distributions across agents with privacy and efficiency.
problem Comparing distributions across agents in a distributed system.
method Decentralized entropic optimal transport with mini-batch randomized block-coordinate descent and decentralized kernel approximation.
result The method provides a privacy-preserving and communication-efficient solution to distributed distribution comparison.
New algorithm computes Schrödinger Bridge for unpaired data translation.
problem Computing optimal transport maps for unpaired data translation.
method Schrödinger Bridge Flow, a discretization of a flow of path measures.
result Eliminates the need to train multiple DDM-like models.
New streaming methods improve convergence rates for optimization problems.
problem Optimizing large-scale, sequential data problems.
method Time-varying mini-batches and Polyak-Ruppert averaging for gradient-based algorithms.
result Time-varying mini-batches and averaging achieve optimal convergence and variance reduction.
With the large rising of complex data, the nonconvex models such as nonconvex loss function and nonconvex regularizer are widely used in machine learning and pattern recognition. In this paper, we propose a class of mini-batch stochastic ADMMs (alternating direction method of multipliers) for solving large-scale noncon…
New statistical properties for mini-batch Cox-NN optimization.
problem Optimizing deep Cox neural networks using mini-batches.
method Developed mini-batch maximum partial-likelihood estimator (mb-MPLE) for Cox-NN.
result mb-MPLE is consistent and achieves optimal convergence rate.
In statistical learning for real-world large-scale data problems, one must often resort to "streaming" algorithms which operate sequentially on small batches of data. In this work, we present an analysis of the information-theoretic limits of mini-batch inference in the context of generalized linear models and low-rank…
We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm. Our theorem describes the convergence of an infinite array of variants of SGD, each of which is associated with a specific probability law governing the data selection rule used to form mini-batches. This is…
We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates th…
Large-scale distributed training of deep neural networks suffer from the generalization gap caused by the increase in the effective mini-batch size. Previous approaches try to solve this problem by varying the learning rate and batch size over epochs and layers, or some ad hoc modification of the batch normalization. W…
The paper analyzes time-dependent streaming data with biased gradient estimates and proposes improved stochastic optimization methods.
problem Stochastic optimization in a streaming setting with time-dependent and biased gradient estimates.
method Analysis of several first-order methods including SGD, mini-batch SGD, and time-varying mini-batch SGD, along with their Polyak-Ruppert averages.
result Time-varying mini-batch SGD methods can break long- and short-range dependence structures, and biased SGD methods can achieve comparable performance to their unbiased counterparts.
Improved robustness in optimization methods using second-order information.
problem Scalability and sensitivity to mini-batch size in optimization methods.
method Mini-Batch Stochastic Variance-Reduced Newton (extttMb−SVRN) algorithm incorporating partial second-order information. result Achieves a fast linear convergence rate independent of mini-batch size for large data sizes.
The paper tackles MSDA by learning dictionary atoms in Wasserstein space.
problem Mitigating data distribution shifts across multiple source domains to target domain.
method Dictionary learning and optimal transport in Wasserstein space; DaDiL algorithm for learning.
result Improved classification performance by 3.15%, 2.29%, and 7.71% in benchmarks.
SINF models transform arbitrary PDFs to target PDFs using 1D slices.
problem Transforming arbitrary probability distributions to target distributions efficiently.
method Iterative Optimal Transport of 1D slices, maximizing Wasserstein distance.
result SINF models generate high-quality samples and competitive density estimates.
Proposes reducing random error in stochastic optimization by variance regularization.
problem Random error accumulation in stochastic optimization algorithms.
method Regularizes learning-rate based on mini-batch variances.
result Speeds up convergence and stabilizes stochastic optimization.
New method reduces variance in complex probabilistic model optimization.
problem High variance in stochastic optimisation of complex models.
method Use recognition network to approximate optimal control variate for each mini-batch.
result Sub-optimal variance reduction is improved with new approach.
In the setting of nonparametric regression, we propose and study a combination of stochastic gradient methods with Nyström subsampling, allowing multiple passes over the data and mini-batches. Generalization error bounds for the studied algorithm are provided. Particularly, optimal learning rates are derived considerin…
In this paper, we develop a new accelerated stochastic gradient method for efficiently solving the convex regularized empirical risk minimization problem in mini-batch settings. The use of mini-batches is becoming a golden standard in the machine learning community, because mini-batch settings stabilize the gradient es…
The paper debiases mini-batch approximations in deep learning for more accurate optimization and uncertainty quantification.
problem Bias in mini-batch approximations distorts the shape of quadratic approximations used in deep learning.
method Developed and evaluated debiasing strategies for mini-batch approximations.
result Debiasing strategies improve the accuracy of second-order optimization and uncertainty quantification in deep learning.
Mini-batch sub-sampling in neural network training is unavoidable, due to growing data demands, memory-limited computational resources such as graphical processing units (GPUs), and the dynamics of on-line learning. In this study we specifically distinguish between static mini-batch sub-sampled loss functions, where mi…
SP-NGD improves deep learning models' generalization with large mini-batch sizes.
problem Worse generalization performance with large mini-batch sizes in deep learning.
method SP-NGD, a natural gradient descent approach for large-scale deep learning.
result SP-NGD achieves similar generalization performance to first-order methods with accelerated convergence and negligible overhead.
Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide improved generalization performance and allows a significantly smaller memory footp…
Paper shows local SGD outperforms mini-batch SGD under certain conditions.
problem Proving local SGD's superiority in distributed learning with heterogeneous data.
method New lower and upper bounds for local SGD under first-order heterogeneity assumptions.
result Local SGD is min-max optimal under certain conditions, resolving understanding of distributed optimization.
We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of passes and the mini-batch size. In particular, we consider the square loss and show that for a unive…
Simple DP algorithms find approximate solutions for nonconvex ERM.
problem Finding approximate solutions to nonconvex ERM problems with privacy.
method Differential privacy, descent directions, line search, mini-batching, two-phase strategy.
result Effective algorithms for nonconvex ERM with privacy guarantees.
Mini-batch optimization has proven to be a powerful paradigm for large-scale learning. However, the state of the art parallel mini-batch algorithms assume synchronous operation or cyclic update orders. When worker nodes are heterogeneous (due to different computational capabilities or different communication delays), s…
New research shows many batch selection methods for training work just as well as full batch training.
problem Finding optimal batch selection methods for training.
method Analysis of mini-batch Gradient Descent (GD) and Stochastic GD (SGD) with various batch selection rules.
result All mini-batch schedules, including deterministic ones, generalize optimally for smooth Lipschitz-convex/nonconvex/strongly-convex loss functions.
HydaLearn dynamically adjusts task weights for better MTL performance.
problem Constant loss weights in MTL lead to poor results due to drifting relevance and varying mini-batch composition.
method HydaLearn uses mini-batch gradients to dynamically adjust task weights.
result HydaLearn improves performance on synthetic and real-world data.
LibAUC optimizes X-risks for AI tasks like CID, LTR, and CLR.
problem Optimizing risk functions in AI for tasks like classification, ranking, and representation learning.
method Developed a new mini-batch pipeline for deep X-risk optimization (DXO) algorithms.
result Achieved great success in solving CID, LTR, and CLR tasks with faster convergence and scalable performance.
This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems. By decoupling algorithmic analysis issues from hardware and software implementation details, we reveal a robust empirical inverse law between mini-…
New findings show mini-batch SGD operates in a 'Edge of Stochastic Stability' regime.
problem Understanding the stability and convergence of mini-batch SGD.
method Analyzing the mini-batch Hessian and its directional curvature.
result Mini-batch SGD operates in a different stability regime (Edge of Stochastic Stability) compared to full-batch GD.
A new method for graph neural networks speeds up inference and training.
problem Challenges in constructing mini-batches for large graphs in graph neural networks.
method Theoretical model of batch construction via maximizing influence score of nodes on outputs.
result Accelerates inference by up to 130x compared to previous methods.
A new method optimizes projection directions for sliced Wasserstein distances.
problem Finding informative projecting directions for sliced Wasserstein distances is computationally expensive.
method Amortized projection optimization to predict directions efficiently.
result Proposed amortized models improve generative modeling performance.
In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained to interpolate the data by driving the empirical loss (classification and regression) close to zero…
We propose a projected semi-stochastic gradient descent method with mini-batch for improving both the theoretical complexity and practical performance of the general stochastic gradient descent method (SGD). We are able to prove linear convergence under weak strong convexity assumption. This requires no strong convexit…
New methods estimate transport-growth pairs in unbalanced optimal transport.
problem Statistical guarantees for Monge-type estimation in unbalanced optimal transport remain limited.
method Developed two estimators for transport-growth pairs under different setups.
result Achieved minimax optimal rate for estimation of transport-growth pairs.
Recently it has been shown that the step sizes of a family of variance reduced gradient methods called the JacSketch methods depend on the expected smoothness constant. In particular, if this expected smoothness constant could be calculated a priori, then one could safely set much larger step sizes which would result i…
Adam optimizer's bias is influenced by mini-batch size and momentum hyperparameters.
problem Understanding how Adam's implicit bias is affected by mini-batch size and momentum parameters.
method Theoretical framework to analyze mini-batch noise's impact on Adam's memory and bias.
result The magnitude of anti-regularization by memory depends on batch size and momentum hyperparameters.
Introduces statistical optimal transport for probabilistic lectures.
problem No specific problem stated; focuses on introduction.
method Lecture-based introduction to statistical optimal transport.
result Provides an introduction to statistical optimal transport.