activity
20242026
collaborators

7 papers

cs.LG2026

Optimistic Dual Averaging Unifies Modern Optimizers

Thomas Pethick, Wanyun Xie, Roman Machacek +1

We introduce SODA, a generalization of Optimistic Dual Averaging, which provides a common perspective on state-of-the-art optimizers like Muon, Lion, AdEMAMix and NAdam, showing th…

cs.LG2026

MaD-Mix: Multi-Modal Data Mixtures via Latent Space Coupling for Vision-Language Model Training

Wanyun Xie, Francesco Tonin, Volkan Cevher

Vision-Language Models (VLMs) are typically trained on a diverse set of multi-modal domains, yet current practices rely on costly manual tuning. We propose MaD-Mix, a principled an…

cs.LG2026

Generalized Gradient Norm Clipping & Non-Euclidean -Smoothness

Thomas Pethick, Wanyun Xie, Mete Erdogan +3

This work introduces a hybrid non-Euclidean optimization method which generalizes gradient norm clipping by combining steepest descent and conditional gradient approaches. The meth…

cs.LG2025

Training Deep Learning Models with Norm-Constrained LMOs

Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos +3

In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO…

cs.LG2025

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

Wanyun Xie, Francesco Tonin, Volkan Cevher

Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and requ…

cs.LG2024

SAMPa: Sharpness-aware Minimization Parallelized

Wanyun Xie, Thomas Pethick, Volkan Cevher

Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires \emph{sequentially} computing two gradients, e…