Uncertainty
Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
Leveraging this flexibility, we implement 47 novel MCBO algorithms and benchmark them against seven existing MCBO solvers and five standard black-box optimization algorithms on ten tasks, conducting over 4000 experiments.
DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models Tao Y ang
DPMs, those inherent factors can be automatically discovered, explicitly represented, and clearly injected into the diffusion process via the sub-gradient fields. To tackle this task, we devise an unsupervised approach named DisDiff, achieving disentangled representation learning in the framework of DPMs.
Nonstationary Sparse Spectral Permanental Process
Existing permanental processes often impose constraints on kernel types or sta-tionarity, limiting the model's expressiveness. To overcome these limitations, we propose a novel approach utilizing the sparse spectral representation of non-stationary kernels.
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
As one of the most mainstream paradigms for sequential decision-making, RL has extensive applications in many real-world problems (Kober et al., 2013; Mnih et al.,
Dynamic Conditional Optimal Transport through Simulation-Free Flows
One way to achieve this is through triangular mappings [Baptista et al., 2020, Spantini et al., 2022],
When Y our AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback Leon Lang University of Amsterdam Davis Foote
Modeling the human as Boltzmann-rational w.r.t. a belief over trajectories, we prove conditions under which RLHF is
