We study the problem of generating diverse candidates in the context of Multi-Objective
Optimization. In many applications of machine learning such as drug discovery and material …

Abstract Machine learning has rapidly evolved during the last decade, achieving expert
human performance on notoriously challenging problems such as image classification. This …

The construction of machine learning models involves many bi-level multiobjective
optimization problems (BL-MOPs), where upper-level (UL) candidate solutions must be …

Reinforcement learning (RL) over text representations can be effective for finding high-value
policies that can search over graphs. However, RL requires careful structuring of the search …

The relentless expansion of deep learning (DL) applications in recent years has prompted a
pivotal shift towards on-device execution, driven by the urgent need for real-time processing …

Active learning is increasingly adopted for expensive multi-objective combinatorial
optimization problems, but it involves a challenging subset selection problem, optimizing the …

The post-training compression based on affine quantization is a common technology to
improve the efficiency of embedded neural network accelerators. Current state-of-the-art …

The post-training quantization (PTQ) is a common technology to improve the efficiency of
embedded neural network accelerators. Existing PTQ schemes for CNN activations usually …