10 citations · 77 across the 28 of their papers we have counts for
28 papers
Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
Xinlei Niu, Christian Walder, Jing Zhang +1
We propose the stochastic optimal path which solves the classical optimal path problem by a probability-softening solution. This unified approach transforms a wide range of DP prob…
DualVAE: Controlling Colours of Generated and Real Images
Keerth Rathakumar, David Liebowitz, Christian Walder +2
Colour controlled image generation and manipulation are of interest to artists and graphic designers. Vector Quantised Variational AutoEncoders (VQ-VAEs) with autoregressive (AR) p…
R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents
Daniel D. Johnson, Daniel Tarlow, Christian Walder
Large language models show impressive results at predicting structured text such as code, but also commonly introduce errors and hallucinations in their output. When used to assist…
Sampled Transformer for Point Sets
Shidi Li, Christian Walder, Alexander Soen +2
The sparse transformer can reduce the computational complexity of the self-attention layers to , whilst still being a universal approximator of continuous sequence-to-sequenc…
LegendreTron: Uprising Proper Multiclass Loss Learning
Kevin Lam, Christian Walder, Spiridon Penev +1
Loss functions serve as the foundation of supervised learning and are often chosen prior to model development. To avoid potentially ad hoc choices of losses, statistical decision t…
Determinantal Point Process Likelihoods for Sequential Recommendation
Yuli Liu, Christian Walder, Lexing Xie
Sequential recommendation is a popular task in academic research and close to real-world application scenarios, where the goal is to predict the next action(s) of the user based on…
SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation
Shidi Li, Christian Walder, Miaomiao Liu
This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity. Our SPA-VAE infers a set of latent canonical candidate…
Dense Uncertainty Estimation
Jing Zhang, Yuchao Dai, Mochu Xiang +7
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks.The former is usually trained to achieve a mapping from input space to…
EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
Shidi Li, Miaomiao Liu, Christian Walder
This paper tackles the problem of parts-aware point cloud generation. Unlike existing works which require the point cloud to be segmented into parts a priori, our parts-aware editi…
Humanly Certifying Superhuman Classifiers
Qiongkai Xu, Christian Walder, Chenchen Xu
Estimating the performance of a machine learning system is a longstanding challenge in artificial intelligence research. Today, this challenge is especially relevant given the emer…
Learning to Continually Learn Rapidly from Few and Noisy Data
Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier +3
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be…
TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
Minchao Wu, Michael Norrish, Christian Walder +1
We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. The proposed framework is able to learn proof search strategies as well as tacti…
MTL2L: A Context Aware Neural Optimiser
Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier +3
Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner. Previously, it was shown that a meta-learner could learn the direct rules to u…
All your loss are belong to Bayes
Christian Walder, Richard Nock
Loss functions are a cornerstone of machine learning and the starting point of most algorithms. Statistics and Bayesian decision theory have contributed, via properness, to elicit…
Quantile Propagation for Wasserstein-Approximate Gaussian Processes
Rui Zhang, Christian J. Walder, Edwin V. Bonilla +2
Approximate inference techniques are the cornerstone of probabilistic methods based on Gaussian process priors. Despite this, most work approximately optimizes standard divergence…
Computer Assisted Composition in Continuous Time
Chamin Hewa Koneputugodage, Rhys Healy, Sean Lamont +9
We address the problem of combining sequence models of symbolic music with user defined constraints. For typical models this is non-trivial as only the conditional distribution of…
Variational Inference for Sparse Gaussian Process Modulated Hawkes Process
Rui Zhang, Christian Walder, Marian-Andrei Rizoiu
The Hawkes process (HP) has been widely applied to modeling self-exciting events including neuron spikes, earthquakes and tweets. To avoid designing parametric triggering kernel an…
New Tricks for Estimating Gradients of Expectations
Christian J. Walder, Paul Roussel, Richard Nock +2
We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions bet…
Efficient Non-parametric Bayesian Hawkes Processes
Rui Zhang, Christian Walder, Marian-Andrei Rizoiu +1
In this paper, we develop an efficient nonparametric Bayesian estimation of the kernel function of Hawkes processes. The non-parametric Bayesian approach is important because it pr…
Monge blunts Bayes: Hardness Results for Adversarial Training
Zac Cranko, Aditya Krishna Menon, Richard Nock +3
The last few years have seen a staggering number of empirical studies of the robustness of neural networks in a model of adversarial perturbations of their inputs. Most rely on an…
Self-Bounded Prediction Suffix Tree via Approximate String Matching
Dongwoo Kim, Christian Walder
Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction. Current prediction techniques for PSTs rely on exact matching between the suffix of t…
Neural Dynamic Programming for Musical Self Similarity
Christian J. Walder, Dongwoo Kim
We present a neural sequence model designed specifically for symbolic music. The model is based on a learned edit distance mechanism which generalises a classic recursion from comp…
Fast Bayesian Intensity Estimation for the Permanental Process
Christian J. Walder, Adrian N. Bishop
The Cox process is a stochastic process which generalises the Poisson process by letting the underlying intensity function itself be a stochastic process. In this paper we present…
Computer Assisted Composition with Recurrent Neural Networks
Christian Walder, Dongwoo Kim
Sequence modeling with neural networks has lead to powerful models of symbolic music data. We address the problem of exploiting these models to reach creative musical goals, by com…