Volkan Cevher

High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups

2018 · arXiv (Cornell University)

Bayesian optimization (BO) is a popular technique for sequential black-box function optimization, with applications including parameter tuning, robotics, environmental monitoring, and more. One of the most important challenges in BO is the development of algorithms …

Lower Bounds on Active Learning for Graphical Model Selection

2017 · Infoscience (Ecole Polytechnique Fédérale de Lausanne)

We consider the problem of estimating the underlying graph associated with a Markov random field, with the added twist that the decoding algorithm can iteratively choose which subsets of nodes to sample based on the …

Revisiting adversarial training for the worst-performing class

2023 · arXiv (Cornell University)

Despite progress in adversarial training (AT), there is a substantial gap between the top-performing and worst-performing classes in many datasets. For example, on CIFAR10, the accuracies for the best and worst classes are 74% and …

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks

2024 · arXiv (Cornell University)

Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks as the curse of dimensionality (CoD) cannot be evaded when trying to approximate even …

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

2024 · arXiv (Cornell University)

Machine unlearning has been used to remove unwanted knowledge acquired by large language models (LLMs). In this paper, we examine machine unlearning from an optimization perspective, framing it as a regularized multi-task optimization problem, where …