Search Results for author: Zhenwen Dai

Found 30 papers, 8 papers with code

In-context Exploration-Exploitation for Reinforcement Learning

no code implementations11 Mar 2024 Zhenwen Dai, Federico Tomasi, Sina Ghiassian

In-context learning is a promising approach for online policy learning of offline reinforcement learning (RL) methods, which can be achieved at inference time without gradient optimization.

Bayesian Inference Bayesian Optimization +3

Automatic Music Playlist Generation via Simulation-based Reinforcement Learning

no code implementations13 Oct 2023 Federico Tomasi, Joseph Cauteruccio, Surya Kanoria, Kamil Ciosek, Matteo Rinaldi, Zhenwen Dai

In this paper, we present a reinforcement learning framework that solves for such limitations by directly optimizing for user satisfaction metrics via the use of a simulated playlist-generation environment.

Collaborative Filtering reinforcement-learning

A Strong Baseline for Batch Imitation Learning

no code implementations6 Feb 2023 Matthew Smith, Lucas Maystre, Zhenwen Dai, Kamil Ciosek

Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making.

Continuous Control Imitation Learning +3

Model Selection for Production System via Automated Online Experiments

no code implementations NeurIPS 2020 Zhenwen Dai, Praveen Chandar, Ghazal Fazelnia, Ben Carterette, Mounia Lalmas-Roelleke

A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production.

Model Selection

Making Differentiable Architecture Search less local

no code implementations21 Apr 2021 Erik Bodin, Federico Tomasi, Zhenwen Dai

Neural architecture search (NAS) is a recent methodology for automating the design of neural network architectures.

Neural Architecture Search

The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies

1 code implementation28 Oct 2020 Simon Damm, Dennis Forster, Dmytro Velychko, Zhenwen Dai, Asja Fischer, Jörg Lücke

Here we show that for standard (i. e., Gaussian) VAEs the ELBO converges to a value given by the sum of three entropies: the (negative) entropy of the prior distribution, the expected (negative) entropy of the observable distribution, and the average entropy of the variational distributions (the latter is already part of the ELBO).

Black-box density function estimation using recursive partitioning

1 code implementation26 Oct 2020 Erik Bodin, Zhenwen Dai, Neill D. F. Campbell, Carl Henrik Ek

We present a novel approach to Bayesian inference and general Bayesian computation that is defined through a sequential decision loop.

Bayesian Inference

Intrinsic Gaussian Processes on Manifolds and Their Accelerations by Symmetry

no code implementations25 Jun 2020 Ke Ye, Mu Niu, Pokman Cheung, Zhenwen Dai, YuAn Liu

The introduction of our strip algorithm, tailored for manifolds with extra symmetries, and the ball algorithm, designed for arbitrary manifolds, constitutes our significant contribution.

Gaussian Processes regression

ProSper -- A Python Library for Probabilistic Sparse Coding with Non-Standard Priors and Superpositions

no code implementations1 Aug 2019 Georgios Exarchakis, Jörg Bornschein, Abdul-Saboor Sheikh, Zhenwen Dai, Marc Henniges, Jakob Drefs, Jörg Lücke

The library widens the scope of dictionary learning approaches beyond implementations of standard approaches such as ICA, NMF or standard L1 sparse coding.

Dictionary Learning

Modulating Surrogates for Bayesian Optimization

no code implementations ICML 2020 Erik Bodin, Markus Kaiser, Ieva Kazlauskaite, Zhenwen Dai, Neill D. F. Campbell, Carl Henrik Ek

Bayesian optimization (BO) methods often rely on the assumption that the objective function is well-behaved, but in practice, this is seldom true for real-world objectives even if noise-free observations can be collected.

Bayesian Optimization Gaussian Processes

Meta-Surrogate Benchmarking for Hyperparameter Optimization

1 code implementation NeurIPS 2019 Aaron Klein, Zhenwen Dai, Frank Hutter, Neil Lawrence, Javier Gonzalez

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 expensive to solve.

Benchmarking Hyperparameter Optimization

Modular Deep Probabilistic Programming

1 code implementation ICLR 2019 Zhenwen Dai, Eric Meissner, Neil D. Lawrence

A probabilistic module consists of a set of random variables with associated probabilistic distributions and dedicated inference methods.

Probabilistic Programming Variational Inference

Variational Information Distillation for Knowledge Transfer

2 code implementations CVPR 2019 Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence, Zhenwen Dai

We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10.

Knowledge Distillation Transfer Learning

Intrinsic Gaussian processes on complex constrained domains

no code implementations3 Jan 2018 Mu Niu, Pokman Cheung, Lizhen Lin, Zhenwen Dai, Neil Lawrence, David Dunson

in-GPs respect the potentially complex boundary or interior conditions as well as the intrinsic geometry of the spaces.

Gaussian Processes valid

Truncated Variational Sampling for "Black Box" Optimization of Generative Models

no code implementations21 Dec 2017 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.

Auto-Differentiating Linear Algebra

no code implementations24 Oct 2017 Matthias Seeger, Asmus Hetzel, Zhenwen Dai, Eric Meissner, Neil D. Lawrence

Development systems for deep learning (DL), such as Theano, Torch, TensorFlow, or MXNet, are easy-to-use tools for creating complex neural network models.

Active Learning Bayesian Optimization +1

Preferential Bayesian Optmization

no code implementations ICML 2017 Javier González, Zhenwen Dai, Andreas Damianou, Neil D. Lawrence

We present a new framework for this scenario that we call Preferential Bayesian Optimization (PBO) and that allows to find the optimum of a latent function that can only be queried through pairwise comparisons, so-called duels.

Bayesian Optimization Recommendation Systems

Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes

2 code implementations NeurIPS 2017 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.

Gaussian Processes Variational Inference

Preferential Bayesian Optimization

no code implementations12 Apr 2017 Javier Gonzalez, Zhenwen Dai, Andreas Damianou, Neil D. Lawrence

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.

Bayesian Optimization Recommendation Systems

Spatio-temporal Gaussian processes modeling of dynamical systems in systems biology

no code implementations17 Oct 2016 Mu Niu, Zhenwen Dai, Neil Lawrence, Kolja Becker

The spatio-temporal field of protein concentration and mRNA expression are reconstructed without explicitly solving the partial differential equation.

Bayesian Inference Gaussian Processes

Unsupervised Learning with Imbalanced Data via Structure Consolidation Latent Variable Model

no code implementations30 Jun 2016 Fariba Yousefi, Zhenwen Dai, Carl Henrik Ek, Neil Lawrence

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 small amount of data.

Variational Inference

Recurrent Gaussian Processes

1 code implementation20 Nov 2015 César Lincoln C. Mattos, Zhenwen Dai, Andreas Damianou, Jeremy Forth, Guilherme A. Barreto, Neil D. Lawrence

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 sequential data.

Gaussian Processes

Variational Auto-encoded Deep Gaussian Processes

no code implementations19 Nov 2015 Zhenwen Dai, Andreas Damianou, Javier González, Neil Lawrence

We develop a scalable deep non-parametric generative model by augmenting deep Gaussian processes with a recognition model.

Bayesian Optimization Gaussian Processes

Spike and Slab Gaussian Process Latent Variable Models

no code implementations10 May 2015 Zhenwen Dai, James Hensman, Neil Lawrence

The Gaussian process latent variable model (GP-LVM) is a popular approach to non-linear probabilistic dimensionality reduction.

Dimensionality Reduction Gaussian Processes +2

GP-select: Accelerating EM using adaptive subspace preselection

no code implementations10 Dec 2014 Jacquelyn A. Shelton, Jan Gasthaus, Zhenwen Dai, Joerg Luecke, Arthur Gretton

We propose a nonparametric procedure to achieve fast inference in generative graphical models when the number of latent states is very large.

Object Localization

Gaussian Process Models with Parallelization and GPU acceleration

no code implementations18 Oct 2014 Zhenwen Dai, Andreas Damianou, James Hensman, Neil Lawrence

In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration.

What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach

no code implementations NeurIPS 2013 Zhenwen Dai, Georgios Exarchakis, Jörg Lücke

By far most approaches to unsupervised learning learning of visual features, such as sparse coding or ICA, account for translations by representing the same features at different positions.

Position

Cannot find the paper you are looking for? You can Submit a new open access paper.