Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Arbel, Michael"'
We address the task of uplifting visual features or semantic masks from 2D vision models to 3D scenes represented by Gaussian Splatting. Whereas common approaches rely on iterative optimization-based procedures, we show that a simple yet effective ag
Externí odkaz:
http://arxiv.org/abs/2410.14462
In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solved by using methods developed i
Externí odkaz:
http://arxiv.org/abs/2403.20233
Autor:
Arbel, Michael, Zouaoui, Alexandre
Replicability in machine learning (ML) research is increasingly concerning due to the utilization of complex non-deterministic algorithms and the dependence on numerous hyper-parameter choices, such as model architecture and training datasets. Ensuri
Externí odkaz:
http://arxiv.org/abs/2402.13831
Publikováno v:
Published in Transactions on Machine Learning Research (TMLR), 2024
Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks. Yet, real-world applications often demand compact models tailored to specific problems. Variants of knowledge distillation have been devised for such a
Externí odkaz:
http://arxiv.org/abs/2402.11305
Data augmentation is known to improve the generalization capabilities of neural networks, provided that the set of transformations is chosen with care, a selection often performed manually. Automatic data augmentation aims at automating this process.
Externí odkaz:
http://arxiv.org/abs/2306.09998
This work studies the global convergence and implicit bias of Gauss Newton's (GN) when optimizing over-parameterized one-hidden layer networks in the mean-field regime. We first establish a global convergence result for GN in the continuous-time limi
Externí odkaz:
http://arxiv.org/abs/2302.02904
We introduce two synthetic likelihood methods for Simulation-Based Inference (SBI), to conduct either amortized or targeted inference from experimental observations when a high-fidelity simulator is available. Both methods learn a conditional energy-
Externí odkaz:
http://arxiv.org/abs/2210.14756
Autor:
Arbel, Michael, Mairal, Julien
Bilevel optimization problems involve two nested objectives, where an upper-level objective depends on a solution to a lower-level problem. When the latter is non-convex, multiple critical points may be present, leading to an ambiguous definition of
Externí odkaz:
http://arxiv.org/abs/2207.04888
We propose Continual Repeated Annealed Flow Transport Monte Carlo (CRAFT), a method that combines a sequential Monte Carlo (SMC) sampler (itself a generalization of Annealed Importance Sampling) with variational inference using normalizing flows. The
Externí odkaz:
http://arxiv.org/abs/2201.13117
Autor:
Arbel, Michael, Mairal, Julien
We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex. Specifically, we consider algorithms based on inexact implicit differentiation a
Externí odkaz:
http://arxiv.org/abs/2111.14580