4 papers
Understanding Differentiable Embeddings Through Differential and Integral Geometry
Xinyu Zhang, Klaus Mueller
How can an analyst decide whether a nonlinear dimensionality reduction embedding can be trusted? Existing diagnostics provide only partial answers: projection glyphs characterize l…
Efficient On-Policy Reinforcement Learning via Exploration of Sparse Parameter Space
Xinyu Zhang, Aishik Deb, Klaus Mueller
Policy-gradient methods such as Proximal Policy Optimization (PPO) are typically updated along a single stochastic gradient direction, leaving the rich local structure of the param…
Smart Starts: Accelerating Convergence through Uncommon Region Exploration
Xinyu Zhang, Mário Antunes, Tyler Estro +2
Initialization profoundly affects evolutionary algorithm (EA) efficacy by dictating search trajectories and convergence. This study introduces a hybrid initialization strategy comb…
Into the Void: Mapping the Unseen Gaps in High Dimensional Data
Xinyu Zhang, Tyler Estro, Geoff Kuenning +2
We present a comprehensive pipeline, augmented by a visual analytics system named ``GapMiner'', that is aimed at exploring and exploiting untapped opportunities within the empty ar…