214 citations · 487 across the 24 of their papers we have counts for
7 papers · 1 filter
Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT
Joery Ariën de Vries, Neil David Lawrence, Zhenwen Dai
Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline over repeated rollouts to red…
A Strong Baseline for Batch Imitation Learning
Matthew Smith, Lucas Maystre, Zhenwen Dai +1
Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making. We provide an easy-to-implement, novel algorithm for imitation l…
Making Differentiable Architecture Search less local
Erik Bodin, Federico Tomasi, Zhenwen Dai
Neural architecture search (NAS) is a recent methodology for automating the design of neural network architectures. Differentiable neural architecture search (DARTS) is a promising…
Meta-Surrogate Benchmarking for Hyperparameter Optimization
Aaron Klein, Zhenwen Dai, Frank Hutter +2
Despite the recent progress in hyperparameter optimization (HPO), available benchmarks that resemble real-world scenarios consist of a few and very large problem instances that are…
Unsupervised Learning with Imbalanced Data via Structure Consolidation Latent Variable Model
Fariba Yousefi, Zhenwen Dai, Carl Henrik Ek +1
Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with…
Recurrent Gaussian Processes
César Lincoln C. Mattos, Zhenwen Dai, Andreas Damianou +3
We define Recurrent Gaussian Processes (RGP) models, a general family of Bayesian nonparametric models with recurrent GP priors which are able to learn dynamical patterns from sequ…
Variational Auto-encoded Deep Gaussian Processes
Zhenwen Dai, Andreas Damianou, Javier González +1
We develop a scalable deep non-parametric generative model by augmenting deep Gaussian processes with a recognition model. Inference is performed in a novel scalable variational fr…