works on

From the 1 of 8 linked papers with an AI index.

collaborators

8 papers

cs.LG2026

Sharp Stability Threshold and Certification for Designing Stable Residual Architectures

Hyemin Gu, Michael Tyrrell, Tuhin Sahai +1

The paper introduces a sublinear‑growth principle that gives a sharp stability condition (input‑magnitude exponent q ≤ 1) for deep residual networks, and provides a method to certi…

cs.LG2026

Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space

Kelvin Kan, Xingjian Li, Benjamin J. Zhang +3

Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology. Existing convergence theory, however, exh…

stat.ML2026

ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks

Zhizhen Zhang, Hyemin Gu, Benjamin J. Zhang +6

Open time-series forecasting (TSF) benchmarks cover retail, energy, weather, and traffic, but supply-chain logistics remains underserved. We introduce ISOMORPH, the first public di…

cs.LG2026

Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

Noah Schwartz, Chandra Kanth Nagesh, Sriram Sankaranarayanan +3

We present a generalized framework for the range verification of neural networks featuring non-linear activation functions. Our approach first constructs an ``optimized piecewise a…

cs.LG2025

Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency

Kelvin Kan, Xingjian Li, Benjamin J. Zhang +3

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture…

cs.LG2025

Stability of Transformers under Layer Normalization

Kelvin Kan, Xingjian Li, Benjamin J. Zhang +4

Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been a…