Paper optimizes training data distribution for better model performance across various deployment conditions.
problem Improving model accuracy when deployed with parameters far from training data.
method Developed adaptive algorithms based on bilevel or alternating optimization in the space of probability measures.
result Optimized training distributions lead to models with improved sample complexity and robustness to distribution shift.
A novel Federated Learning scheme using Optimal Transport for personalized model training.
problem Training models with data from clients having non-identically distributed data.
method Personalized Federated Learning scheme based on Optimal Transport (FedOT).
result FedOT scheme effectively transfers data from multiple distributions to a common domain and optimizes the prediction model.
Study optimal ridge regularization for out-of-distribution prediction.
problem Optimal ridge regularization for predicting out-of-distribution data.
method Established conditions for optimal regularization under covariate and regression shifts, proving monotonic risk in data aspect ratio.
result Negative regularization can be optimal under shifts, even with isotropic or underparameterized training features.
Enhances flexibility in data reweighting with optimal transport and maximum entropy principles.
problem Adapting empirical distributions to predefined constraints on moments, tail behavior, etc.
method Nonparametric distributional constraints, maximum entropy principle, optimal transport.
result Maximum entropy weight adjusted empirical distribution close to a specified distribution in optimal transport metric.
Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which can be important for datasets such as facial images. A GAN can transform a simple…
New insights into noise distribution for self-supervised learning.
problem Challenges the assumption that optimal noise should match data distribution.
method Turns to Noise-Contrastive Estimation (NCE) to define optimality of noise distribution.
result Optimal noise distribution is different from data distribution, challenging GANs assumption.
A new method for conditional sampling using paired Wasserstein Autoencoders.
problem Conditional sampling from complex data distributions.
method Derive a novel loss function for Wasserstein Autoencoders to enable sampling from OT-type couplings.
result Learned cost-optimal transport maps and conditional sampling from an OT-type coupling.
PerfGD solves model-induced data shifts by finding optimal points.
problem Model-induced data shifts where model choice changes data distribution.
method Performative Gradient Descent (PerfGD) which explicitly captures model-data interactions.
result PerfGD provably converges to performatively optimal point.
New binary AA methods improve on existing techniques.
problem Binary data limitations in AA methods.
method Proposed two optimization frameworks for binary AA.
result Superior performance on synthetic and real binary data.
Study optimizes privacy in distributed optimization, balancing accuracy and communication.
problem Privacy-preserving distributed stochastic convex optimization.
method Distributed algorithm using Vaidya's plane cutting method, with privacy guarantees via differential privacy.
result Complete characterization of accuracy-communication-privacy trade-off.
A novel framework synthesizes treatment data across sites using optimal transport.
problem Estimating treatment effects across different sites with varying conditions.
method Distributional causal inference, Optimal Transport for alignment of control group distributions.
result Synthetic treatment group data aligns with true target distribution under general conditions.
The paper solves the problem of optimal portfolio choice when the parameters of the asset returns distribution, like the mean vector and the covariance matrix are unknown and have to be estimated by using historical data of the asset returns. The new approach employs the Bayesian posterior predictive distribution which…
CAdam optimizes online learning by adapting to distribution shifts and noise.
problem Challenges in online learning data, including distribution shifts and noise, affect Adam's performance.
method CAdam uses a confidence-based approach to assess the consistency between momentum and gradients before updating parameters.
result CAdam outperforms other optimizers in various settings with distribution shift or noise.
Proposes using Wasserstein barycenters for robust optimization with multiple data sources.
problem Distributionally robust optimization with multiple heterogeneous data sources.
method Construct nominal distribution through Wasserstein barycenter of multiple data samples, reformulates as a finite convex program.
result Proposed scheme outperforms other estimators in sparse inverse covariance matrix estimation.
New methods improve distributed optimization on non-iid data.
problem Communication bottleneck in distributed machine learning models.
method Two types of distributed gradient compression methods (D-QSGD and D-EF-SGD) analyzed for non-iid data.
result D-EF-SGD performs better than D-QSGD on non-iid data but can still slow down with high data skewness.
Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms. The distributional uncertainty size is often shown to correspond to the regularization parameter. The type of regularization (e.g. the norm used to regularize)…
New findings show optimal noise in contrastive learning is not the same as data distribution.
problem The optimal noise distribution in contrastive learning is not the same as the data distribution.
method Empirical and theoretical analysis of contrastive learning methods.
result Deviation from the assumption of equal noise and data distribution leads to better statistical estimators.
This paper optimizes subsampling for large datasets using Poisson distribution.
problem Efficiently subsample large datasets for quasi-likelihood estimation.
method Derives optimal Poisson subsampling probabilities and develops a distributed subsampling framework.
result Consistent and asymptotically normal estimators are obtained.
SHIFT method optimally estimates heterogeneous discrete distributions with limited communication.
problem Collaborative learning of discrete distributions under heterogeneity and communication constraints.
method Two-stage method: First, users learn a central distribution; then, fine-tune this to estimate individual distributions.
result SHIFT is minimax optimal in the model of heterogeneity and under communication constraints.
This paper reviews methods for distributed training of machine learning models from high-rate streams.
problem Training machine learning models from high-rate distributed streams in a compute- and bandwidth-limited setting.
method Recently developed methods for large-scale distributed stochastic optimization.
result There exist regimes where systems can learn from distributed, streaming data at order-optimal rates.
This paper introduces DCE for better counterfactual explanations using optimal transport.
problem Lack of nuanced distributional characteristics in existing counterfactual explanations.
method Formulates a chance-constrained optimization problem using optimal transport to derive counterfactual distributions.
result DCE provides deeper insights into decision-making models by aligning counterfactual distributions with factual ones.
New method for optimal transport with missing data, debiased and efficient.
problem Solving optimal transport between two distributions with missing values.
method Debiasing Wasserstein distance for empirical Gaussian distributions, entropic regularized optimal transport using ISVT.
result Efficient and consistent estimation of entropic regularized optimal transport.
Optimizes decisions without knowing the true distribution using historical data.
problem Optimizing decisions without knowing the true distribution.
method Combines sampling and bisection search algorithms to solve an optimization problem.
result Proves sufficient conditions for local out-of-sample optimality.
Optimal income crossover found using particle swarm optimization.
problem Determining the crossover point between two income distributions.
method Particle swarm optimization for finding crossover income, temperature, and Pareto index.
result Optimization method finds boundaries of two income distributions.
Ringleader ASGD optimizes SGD for diverse edge devices with varying data and computation speeds.
problem Scalable distributed optimization with heterogeneous devices and data.
method Ringleader ASGD, an asynchronous SGD algorithm.
result Achieves optimal time complexity under data heterogeneity and arbitrary computation speeds.
Paper introduces ITD for detecting distributional changes in decentralized learning environments.
problem Detecting distributional changes in decentralized learning environments with data privacy and heterogeneity concerns.
method Introduces Integrated Transportation Distance (ITD) for two-sample testing in federated learning.
result ITD effectively aggregates information across distributed clients, detecting subtle distributional shifts.
A new flow optimizes synthetic data alignment for generative modeling.
problem Optimizing synthetic data to match target distributions.
method Score difference (SD) flow to reduce KL divergence.
result SD flow provides a theoretical link between generative models.
As the size of modern data sets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing. Given that optimization is one of the pillars of machine learning and predictive modeling, distributed optimization methods have recently garne…
Paper tackles distributed linear regression with compositional covariates.
problem Solving distributed statistical methodology and computing for massive compositional data.
method Proposes two distributed optimization techniques based on ADMM and CDMM for solving constrained convex optimization problems.
result Established convergence theories for the proposed algorithms under regularity conditions.
Paper proves conformal prediction works for any data distribution.
problem Quantifying risk in AI systems with non-exchangeable data.
method Developed a method to extend conformal prediction to any data distribution.
result Valid conformal prediction guarantees for any data distribution.
Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model. However, calculating exact posterior distributions is intractable for all but the simplest models. Consequently, efficient computation of an approximate posterior distributio…
Machine learning with big data often involves large optimization models. For distributed optimization over a cluster of machines, frequent communication and synchronization of all model parameters (optimization variables) can be very costly. A promising solution is to use parameter servers to store different subsets of…
A distributed algorithm for training graph convolutional networks.
problem Training graph convolutional networks with sparse network topology and distributed agents.
method Formulate inference and optimization in a distributed scenario, propose a gradient descent procedure, and design communication topology.
result Convergence to stationary solutions of the GCN training problem under mild conditions.
Develops estimators for near-optimal linear regression under distribution shift.
problem Linear regression under distribution shift with scarce target domain data.
method Minimax linear risk estimators covering various transfer learning settings.
result Achieves near-optimal risk for linear regression problems under distribution shift.
Efficiently estimates distributed mean with side information, near-optimal and universal.
problem Distributed mean estimation with side information in communication constrained settings.
method Wyner-Ziv estimators for communication and computation efficiency.
result Near-optimal and universal recovery guarantees for distributed optimization and compression.
Diffusion models achieve nearly optimal distribution estimation in various spaces.
problem Theoretical limitations of diffusion modeling for distribution estimation.
method Analysis of approximation and generalization abilities of diffusion models in Besov spaces.
result Diffusion models achieve nearly minimax optimal estimation rates in total variation and Wasserstein distances.
Paper proposes a new framework to improve policy optimization by aligning real and simulated data distributions.
problem Inaccurate model estimation leads to performance degradation in model-based reinforcement learning.
method Introduces unsupervised model adaptation to minimize the IPM between real and simulated data distributions.
result Achieves state-of-the-art performance in sample efficiency on various continuous control tasks.
Stochastic algo learns from evolving data, achieving optimal performance.
problem Performative prediction and multiplayer extensions.
method Stochastic approximation with decision-dependent distributions.
result Asymptotic normality and optimality of the algorithm's performance.
New framework for robust regularization under uncertain data distributions.
problem Addressing ill-posed inverse problems and statistical estimation under distributional uncertainty.
method Distributionally robust optimal regularization using convex duality.
result Identifies robust regularizers that remain effective under data distributional perturbations.
A decision-theoretic bootstrapping method for robust uncertainty quantification.
problem Uncertainty in finite data sets and distributional shift between training and testing data.
method Partition data, train models, sample UQ subsets, define adversarial game, identify optimal mixed strategies.
result Optimal model mixtures and UQ estimates for robust uncertainty quantification.
TC-VAE generates robust financial time series data with causal constraints.
problem Generating realistic financial time series data with causal relationships.
method TC-VAE with causality constraint, RealNVP prior, and Wasserstein distance.
result TC-VAE loss controls discrepancy between market and generated distributions.
Improved Adam for time series forecasting with distributional drift.
problem Non-stationary data challenges Adam's effectiveness.
method Proposed TS_Adam, removing Adam's second-order bias correction.
result TS_Adam achieves 12.8% reduction in MSE and 5.7% in MAE on ETT datasets.
New research shows Byzantine failures hurt generalization more than data poisoning in robust distributed learning.
problem Generalization in robust distributed learning algorithms under Byzantine failures vs. data poisoning.
method Algorithmic stability analysis of robust distributed learning algorithms.
result Byzantine failures yield strictly worse generalization rates than data poisoning.
Method constructs uniformly valid prediction sets across multiple distributions.
problem Uniformly valid prediction sets across multiple distributions.
method Max-p aggregation scheme and optimization programs.
result Optimal and efficient prediction sets for multiple distributions.
FedSmart optimizes federated learning models for non-IID data.
problem Model performance on non-IID data is poor and privacy is at risk.
method FedSmart optimizes models by sharing global gradients and adjusting weights based on local validation set accuracy.
result FedSmart improves model performance by allocating more weight to similar data distributions.
Oracle-efficient algorithm for offline RL with partial data coverage.
problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.
New method uses optimal transport to improve conformal prediction under distribution shifts.
problem Improving conformal prediction's coverage in non-exchangeable settings.
method Optimal transport to estimate and mitigate distribution shifts.
result Estimates and mitigates loss in coverage for arbitrary distribution shifts.
In federated distributed learning, the goal is to optimize a global training objective defined over distributed devices, where the data shard at each device is sampled from a possibly different distribution (a.k.a., heterogeneous or non i.i.d. data samples). In this paper, we generalize the local stochastic and full gr…