GitHub

muhammedanazkhan-oss/SAHR_EA_code_release

Reference implementation and reproduction scripts for SAHR-EA, an optimization framework for expensive, low-variance, model-uncertain and constrained problems. Everything is deterministic under fixed ...
GitHub

Optimize any AI kernel, anywhere.

Autocomp is a portable, extensible framework for LLM-driven kernel optimization across tensor accelerators. Point it at a kernel, pick your hardware target, and Autocomp speeds it up, automatically.
IEEE

Privacy Distributed Constrained Optimization Over Time-Varying Unbalanced Networks and Its Application in Federated Learning

Abstract: This paper investigates a class of constrained distributed zeroth-order optimization (ZOO) problems over time-varying unbalanced graphs while ensuring privacy preservation among individual ...
IEEE

Constrained Evolutionary Bayesian Optimization for Expensive Constrained Optimization Problems With Inequality Constraints

Abstract: This article proposes a constrained evolutionary Bayesian optimization (CEBO) algorithm to cope with expensive constrained optimization problems with inequality constraints. The uniqueness ...