GitHub

SuiMikasa/ATA-Approximation-Algorithm

The ATA algorithm provides a novel approximation framework for analytic functions that cannot be expressed in closed-form via elementary or algebraic functions. It introduces a hybrid approximation ...
GitHub

Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

We propose the Trust Region Preference Approximation (TRPA) algorithm ⚙️, which integrates rule-based optimization with preference-based optimization for LLM reasoning tasks 🤖🧠. As a ...
IEEE

Design of Hardware-Efficient Inexact Multiplier Using Evolutionary Algorithm Factored by Multi-Variate Approximation

Abstract: In the current era of technology, multipliers are integral to various hardware accelerators, making the design of efficient multipliers increasingly essential. This research introduces a ...
IEEE

An Inner Approximation Algorithm for Dynamic Optimization With Strict Satisfaction of Path Constraints

Abstract: An inner approximation algorithm is proposed for path-constrained dynamic optimization (PCDO) by iteratively solving restrictions of PCDO (RPCDO). First, an upper bound function of the path ...