214 citations · 487 across the 24 of their papers we have counts for
26 papers
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…
Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
Federico Tomasi, Joseph Cauteruccio, Surya Kanoria +3
Personalization of playlists is a common feature in music streaming services, but conventional techniques, such as collaborative filtering, rely on explicit assumptions regarding c…
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…
Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics
Mu Niu, Zhenwen Dai, Pokman Cheung +1
This article presents a novel approach to construct Intrinsic Gaussian Processes for regression on unknown manifolds with probabilistic metrics (GPUM) in point clouds. In many real…
Model Selection for Production System via Automated Online Experiments
Zhenwen Dai, Praveen Chandar, Ghazal Fazelnia +2
A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production. As a model is often an intermediate component…
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…
The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
Simon Damm, Dennis Forster, Dmytro Velychko +3
The central objective function of a variational autoencoder (VAE) is its variational lower bound (the ELBO). Here we show that for standard (i.e., Gaussian) VAEs the ELBO converges…
Black-box density function estimation using recursive partitioning
Erik Bodin, Zhenwen Dai, Neill D. F. Campbell +1
We present a novel approach to Bayesian inference and general Bayesian computation that is defined through a sequential decision loop. Our method defines a recursive partitioning o…
Intrinsic Gaussian Processes on Manifolds and Their Accelerations by Symmetry
Ke Ye, Mu Niu, Pokman Cheung +2
Amidst the growing interest in nonparametric regression, we address a significant challenge in Gaussian processes(GP) applied to manifold-based predictors. Existing methods primari…
ProSper -- A Python Library for Probabilistic Sparse Coding with Non-Standard Priors and Superpositions
Georgios Exarchakis, Jörg Bornschein, Abdul-Saboor Sheikh +4
ProSper is a python library containing probabilistic algorithms to learn dictionaries. Given a set of data points, the implemented algorithms seek to learn the elementary component…
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…
Variational Information Distillation for Knowledge Transfer
Sungsoo Ahn, Shell Xu Hu, Andreas Damianou +2
Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student n…
Intrinsic Gaussian processes on complex constrained domains
Mu Niu, Pokman Cheung, Lizhen Lin +3
We propose a class of intrinsic Gaussian processes (in-GPs) for interpolation, regression and classification on manifolds with a primary focus on complex constrained domains or irr…
Truncated Variational Sampling for "Black Box" Optimization of Generative Models
Jörg Lücke, Zhenwen Dai, Georgios Exarchakis
We investigate the optimization of two probabilistic generative models with binary latent variables using a novel variational EM approach. The approach distinguishes itself from pr…
Auto-Differentiating Linear Algebra
Matthias Seeger, Asmus Hetzel, Zhenwen Dai +2
Development systems for deep learning (DL), such as Theano, Torch, TensorFlow, or MXNet, are easy-to-use tools for creating complex neural network models. Since gradient computatio…
Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes
Zhenwen Dai, Mauricio A. Álvarez, Neil D. Lawrence
Often in machine learning, data are collected as a combination of multiple conditions, e.g., the voice recordings of multiple persons, each labeled with an ID. How could we build a…
Preferential Bayesian Optimization
Javier Gonzalez, Zhenwen Dai, Andreas Damianou +1
Bayesian optimization (BO) has emerged during the last few years as an effective approach to optimizing black-box functions where direct queries of the objective are expensive. In…
Spatio-temporal Gaussian processes modeling of dynamical systems in systems biology
Mu Niu, Zhenwen Dai, Neil Lawrence +1
Quantitative modeling of post-transcriptional regulation process is a challenging problem in systems biology. A mechanical model of the regulatory process needs to be able to descr…
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…
Spike and Slab Gaussian Process Latent Variable Models
Zhenwen Dai, James Hensman, Neil Lawrence
The Gaussian process latent variable model (GP-LVM) is a popular approach to non-linear probabilistic dimensionality reduction. One design choice for the model is the number of lat…
Batch Bayesian Optimization via Local Penalization
Javier González, Zhenwen Dai, Philipp Hennig +1
The popularity of Bayesian optimization methods for efficient exploration of parameter spaces has lead to a series of papers applying Gaussian processes as surrogates in the optimi…
GP-select: Accelerating EM using adaptive subspace preselection
Jacquelyn A. Shelton, Jan Gasthaus, Zhenwen Dai +2
We propose a nonparametric procedure to achieve fast inference in generative graphical models when the number of latent states is very large. The approach is based on iterative lat…