21 citations · 58 across the 17 of their papers we have counts for
18 papers
Gaussian Flow-Matching Schedules: Implications for Sampling and Training
Arsène Claustre, Hugo Negrel, Claire Boyer +2
Flow-matching schedules affect both sampling dynamics and the variance of the regression target. For centered commuting Gaussians, we show that a direction-dependent schedule decom…
Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
Valérie Castin, Kimia Nadjahi, Pierre Ablin +1
Low-Rank Adaptation (LoRA) is the most widely adopted method for fine-tuning large language models. Notably, LoRA is inherently overparameterized: multiple pairs of low-rank factor…
Expected Batch Optimal Transport Plans and Consequences for Flow Matching
Samuel Boïté, Julie Delon, Kimia Nadjahi
Solving optimal transport (OT) on random minibatches is a common surrogate for exact OT in large-scale learning. In flow matching (FM), this surrogate is used to obtain OT-like cou…
Convergence Rates for Distribution Matching with Sliced Optimal Transport
Gauthier Thurin, Claire Boyer, Kimia Nadjahi
We study the slice-matching scheme, an efficient iterative method for distribution matching based on sliced optimal transport. We investigate convergence to the target distribution…
Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
Milad Sefidgaran, Kimia Nadjahi, Abdellatif Zaidi
In this paper, we leverage stochastic projection and lossy compression to establish new conditional mutual information (CMI) bounds on the generalization error of statistical learn…
Optimal Transport-based Conformal Prediction
Gauthier Thurin, Kimia Nadjahi, Claire Boyer
Conformal Prediction (CP) is a principled framework for quantifying uncertainty in blackbox learning models, by constructing prediction sets with finite-sample coverage guarantees.…
Slicing Mutual Information Generalization Bounds for Neural Networks
Kimia Nadjahi, Kristjan Greenewald, Rickard Brüel Gabrielsson +1
The ability of machine learning (ML) algorithms to generalize well to unseen data has been studied through the lens of information theory, by bounding the generalization error with…
Asymmetry in Low-Rank Adapters of Foundation Models
Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi +6
Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effecti…
Federated Wasserstein Distance
Alain Rakotomamonjy, Kimia Nadjahi, Liva Ralaivola
We introduce a principled way of computing the Wasserstein distance between two distributions in a federated manner. Namely, we show how to estimate the Wasserstein distance betwee…
Slicing Unbalanced Optimal Transport
Clément Bonet, Kimia Nadjahi, Thibault Séjourné +2
Optimal transport (OT) is a powerful framework to compare probability measures, a fundamental task in many statistical and machine learning problems. Substantial advances have been…
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances
Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy +1
The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance. Yet, the literature on its statistical prope…
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob +2
The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational…
Statistical and Topological Properties of Sliced Probability Divergences
Kimia Nadjahi, Alain Durmus, Lénaïc Chizat +3
The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and…
Generalized Sliced Distances for Probability Distributions
Soheil Kolouri, Kimia Nadjahi, Umut Simsekli +1
Probability metrics have become an indispensable part of modern statistics and machine learning, and they play a quintessential role in various applications, including statistical…
Approximate Bayesian Computation with the Sliced-Wasserstein Distance
Kimia Nadjahi, Valentin De Bortoli, Alain Durmus +2
Approximate Bayesian Computation (ABC) is a popular method for approximate inference in generative models with intractable but easy-to-sample likelihood. It constructs an approxima…
Safe Policy Improvement with Soft Baseline Bootstrapping
Kimia Nadjahi, Romain Laroche, Rémi Tachet des Combes
Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI)…
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance
Kimia Nadjahi, Alain Durmus, Umut Şimşekli +1
Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popula…
Generalized Sliced Wasserstein Distances
Soheil Kolouri, Kimia Nadjahi, Umut Simsekli +2
The Wasserstein distance and its variations, e.g., the sliced-Wasserstein (SW) distance, have recently drawn attention from the machine learning community. The SW distance, specifi…