10 citations · 77 across the 28 of their papers we have counts for
15 papers · 1 filter
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…
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…
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…
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…
Semi-Supervised Kernel PCA
Christian Walder, Ricardo Henao, Morten Mørup +1
We present three generalisations of Kernel Principal Components Analysis (KPCA) which incorporate knowledge of the class labels of a subset of the data points. The first, MV-KPCA,…