6 papers
Depth Enables Local Entropy: Quadratic Depth Dependence in Deep Variation-Norm ReLU Regression
Tao Jiang, Minbo Gao, Shaowei Cai
We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L, width w, layer-sum variation budget A, and output bound B. For this…
Polynomial-Time Singular Witnesses for Non-SNS Sign Patterns
Tao Jiang, Minbo Gao, Shaowei Cai
Sign-nonsingularity asks whether every real matrix with prescribed entry signs is nonsingular. Polynomial-time algorithms recognize square sign-nonsingular patterns through their c…
A Better Analysis For PPSZ For 3-SAT
Tao Jiang, Shaowei Cai
We revisit Scheder's analysis of the original PPSZ algorithm. Keeping his regular and irregular estimates unchanged, we express them in common structural coordinates and replace on…
EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
Tao Jiang, Xinmeng Yu, Chenhao Yi +5
Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantl…
Beyond Speedups: Hardware-Aware Evaluation of Evolutionary Algorithms on GPUs
Xinmeng Yu, Tao Jiang, Ran Cheng +2
Evolutionary algorithms (EAs) are increasingly executed on graphics processing units (GPUs) to exploit population-level parallelism. This shift changes the resource model under whi…
Evolutionary Generative Optimization: Towards Fully Data-Driven Evolutionary Optimization via Generative Learning
Tao Jiang, Kebin Sun, Zhenyu Liang +3
Recent advances in data-driven evolutionary algorithms (EAs) have demonstrated the potential of leveraging historical data to improve optimization accuracy and adaptability. Despit…