9 papers
Learning When to Adapt
Ali Zindari, Xiaowen Jiang, Rotem Mulayoff +1
Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method, yet its learned correction is static: the same low-rank update is applied to every input. This i…
A practical randomized trust-region method to escape saddle points in high dimension
Radu-Alexandru Dragomir, Xiaowen Jiang, Bonan Sun +1
Without randomization, escaping the saddle points of requires at least pieces of information about (values, gradients, Hessian-vec…
Enhancing LLM Training via Spectral Clipping
Xiaowen Jiang, Andrei Semenov, Sebastian U. Stich
While spectral-based optimizers like Muon operate directly on the spectrum of updates, standard adaptive methods such as AdamW do not account for the spectral structure of weights…
Non-Convex Federated Optimization under Cost-Aware Client Selection
Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Different federated optimization algorithms typically employ distinct client-selection strategies: some methods communicate only with a randomly sampled subset of clients at each r…
FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
Yuki Takezawa, Anastasia Koloskova, Xiaowen Jiang +1
Recently, a new optimization method based on the linear minimization oracle (LMO), called Muon, has been attracting increasing attention since it can train neural networks faster t…
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
Yuki Takezawa, Xiaowen Jiang, Anton Rodomanov +1
Reducing communication complexity is critical for efficient decentralized optimization. The proximal decentralized optimization (PDO) framework is particularly appealing, as method…
Stabilized Proximal-Point Methods for Federated Optimization
Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
In developing efficient optimization algorithms, it is crucial to account for communication constraints -- a significant challenge in modern Federated Learning. The best-known comm…
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
Anton Rodomanov, Xiaowen Jiang, Sebastian Stich
We present adaptive gradient methods (both basic and accelerated) for solving convex composite optimization problems in which the main part is approximately smooth (a.k.a. …
Federated Optimization with Doubly Regularized Drift Correction
Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Federated learning is a distributed optimization paradigm that allows training machine learning models across decentralized devices while keeping the data localized. The standard m…