collaborators

5 papers

cs.LG2026

On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers

Sixu Li, Thomas Jacob Maranzatto, Jan Peszek +5

We study the inference-time behavior of deep linear encoder-only transformers through the lens of interacting particle systems. In this perspective, tokens are modeled as particles…

math.OC2026

Optimal drift optimizer for non-convex optimization

Qin Li, Sixu Li, Eitan Tadmor +1

We study a finite-horizon stochastic control criterion for non-convex optimization in which Brownian exploration is balanced against a quadratic control cost. Rather than emphasizi…

cs.LG2026

Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement

Keshu Wu, Sixu Li, Zihao Li +3

Sensor networks increasingly govern modern infrastructure, yet the data they lose are rarely missing in the uniform-random patterns assumed by standard imputation benchmarks. Loop…

cs.LG2025

Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization

Nicolás García Trillos, Aditya Kumar Akash, Sixu Li +2

Adversarial attacks pose significant challenges in many machine learning applications, particularly in the setting of distributed training and federated learning, where malicious a…

math.OC2025

CBO: Consensus-Based Bi-Level Optimization

Nicolás García Trillos, Sixu Li, Konstantin Riedl +1

Bi-level optimization problems, where one wishes to find the global minimizer of an upper-level objective function over the globally optimal solution set of a lower-level objective…