arXiv research

New approach to machine learning optimization using distribution space.

Study optimal ridge regularization for out-of-distribution prediction.

Study optimizes privacy in distributed optimization, balancing accuracy and communication.

Study learns optimal auctions from corrupted or perturbed bidder valuation samples.

Paper optimizes training data distribution for better model performance across various deployment conditions.

A novel Federated Learning scheme using Optimal Transport for personalized model training.

Proposes MRO to achieve uniformly low regret in distributionally robust learning.

The paper studies robust risk measures with linear penalties under uncertain distributions.

Private KL distribution estimation improved with instance-optimality.

LOT embeds distributions for linear separability and classification.

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…

Method learns conditional distributions using neural entropic optimal transport.

FedAVOT improves federated learning by aligning user distributions.

Study binary hypothesis testing with privacy and communication constraints.

New approach for distributed online optimization of non-convex losses with sublinear regret.

New method AM learns optimal vector fields for entire distribution sequences, matching OT.

AOT aligns LLMs on distributional preferences via optimal transport.

Study on distributed nonparametric function estimation with optimal rate and cost of adaptation.

The paper optimizes k-NN for distributed learning with minimax optimal performance.

This paper tackles cost-sensitive portfolio optimization under ambiguous return distributions.

Study efficient iterative method for distribution matching using sliced optimal transport.

New RL algorithm minimizes distributional learning error.

Enhances flexibility in data reweighting with optimal transport and maximum entropy principles.

Paper proposes a method to solve log-optimal portfolios under ambiguous return distributions.

Generates samples conditioned on labels using optimal transport.

We consider $K$-armed stochastic bandits and consider cumulative regret bounds up to time $T$. We are interested in strategies achieving simultaneously a distribution-free regret bound of optimal order $\sqrt{KT}$ and a distribution-dependent regret that is asymptotically optimal, that is, matching the $κ\ln T$ lower b…

Integrates estimation and optimization for uncertain parameters.

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…

Distributed Lion optimizes large model training by reducing communication costs.

The thesis presents a new perspective on high-dimensional optimization.

A new method for conditional sampling using paired Wasserstein Autoencoders.

Bayesian optimization has become a popular method for high-throughput computing, like the design of computer experiments or hyperparameter tuning of expensive models, where sample efficiency is mandatory. In these applications, distributed and scalable architectures are a necessity. However, Bayesian optimization is mo…

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…

New insights into noise distribution for self-supervised learning.

Optimal transport for vector Gaussian mixtures improves efficiency and structure preservation.

Optimizes risk measures given known marginal distributions of two unknown factors.

A new distributed method for convex optimization over networks with fast convergence.

Develops a method to efficiently compute Wasserstein barycenters with variational distributions.

This paper examines how optimization methods affect the reliability of detecting inputs outside a model's training distribution.

A new method solves distributed optimization problems over networks.

New algorithm reduces individual regret and communication costs in cooperative bandits.

This work shows that Gaussian is the only prior for optimal linear estimation in $L^1$ loss.

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…

Optimizes forecast distributions for financial risk management.

Optimal portfolio selection problems are determined by the (unknown) parameters of the data generating process. If an investor wants to realise the position suggested by the optimal portfolios, he/she needs to estimate the unknown parameters and to account for the parameter uncertainty in the decision process. Most oft…

In this letter, we derive the optimal discriminant functions for modulation classification based on the sampled distribution distance. The proposed method classifies various candidate constellations using a low complexity approach based on the distribution distance at specific testpoints along the cumulative distributi…

Optimal income crossover found using particle swarm optimization.

Improved portfolio optimization using VaR and CVaR with NMVM models.