
Unlocking Pixels for Reinforcement Learning via Implicit Attention
There has recently been significant interest in training reinforcement l...
read it

SubLinear Memory: How to Make Performers SLiM
The Transformer architecture has revolutionized deep learning on sequent...
read it

Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
We investigate the influence of adversarial training on the interpretabi...
read it

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Transparency of algorithmic systems entails exposing system properties t...
read it

Now You See Me (CME): Conceptbased Model Extraction
Deep Neural Networks (DNNs) have achieved remarkable performance on a ra...
read it

On the Fairness of Causal Algorithmic Recourse
While many recent works have studied the problem of algorithmic fairness...
read it

Rethinking Attention with Performers
We introduce Performers, Transformer architectures which can estimate re...
read it

Machine Learning Explainability for External Stakeholders
As machine learning is increasingly deployed in highstakes contexts aff...
read it

An Ode to an ODE
We present a new paradigm for Neural ODE algorithms, calledODEtoODE, whe...
read it

Getting a CLUE: A Method for Explaining Uncertainty Estimates
Both uncertainty estimation and interpretability are important factors f...
read it

UFOBLO: Unbiased FirstOrder Bilevel Optimization
Bilevel optimization (BLO) is a popular approach with many applications ...
read it

Masked Language Modeling for Proteins via Linearly Scalable LongContext Transformers
Transformer models have achieved stateoftheart results across a diver...
read it

Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks
Influence maximization is a widely studied topic in network science, whe...
read it

Adversarial Graph Embeddings for Fair Influence Maximization over SocialNetworks
Influence maximization is a widely studied topic in network science, whe...
read it

Time Dependence in NonAutonomous Neural ODEs
Neural Ordinary Differential Equations (ODEs) are elegant reinterpretati...
read it

Dimensions of Diversity in Human Perceptions of Algorithmic Fairness
Algorithms are increasingly involved in making decisions that affect hum...
read it

Evaluating and Aggregating Featurebased Model Explanations
A featurebased model explanation denotes how much each input feature co...
read it

CWY Parametrization for Scalable Learning of Orthogonal and Stiefel Matrices
In this paper we propose a new approach for optimization over orthogonal...
read it

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
With the recent wave of progress in artificial intelligence (AI) has com...
read it

Stochastic Flows and Geometric Optimization on the Orthogonal Group
We present a new class of stochastic, geometricallydriven optimization ...
read it

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
We introduce a framework for dynamic adversarial discovery of informatio...
read it

An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
The notion of individual fairness requires that similar people receive s...
read it

Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks
We study the problem of causal discovery through targeted interventions....
read it

Explainable Machine Learning in Deployment
Explainable machine learning seeks to provide various stakeholders with ...
read it

The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
Causal approaches to fairness have seen substantial recent interest, bot...
read it

Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models
We consider distributed optimization under communication constraints for...
read it

Orthogonal Estimation of Wasserstein Distances
Wasserstein distances are increasingly used in a wide variety of applica...
read it

Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018)
This is the Proceedings of the 2018 ICML Workshop on Human Interpretabil...
read it

A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
Discrimination via algorithmic decision making has received considerable...
read it

Blind Justice: Fairness with Encrypted Sensitive Attributes
Recent work has explored how to train machine learning models which do n...
read it

Structured Evolution with Compact Architectures for Scalable Policy Optimization
We present a new method of blackbox optimization via gradient approximat...
read it

Bucket Renormalization for Approximate Inference
Probabilistic graphical models are a key tool in machine learning applic...
read it

Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction
As algorithms are increasingly used to make important decisions that aff...
read it

Gauged MiniBucket Elimination for Approximate Inference
Computing the partition function Z of a discrete graphical model is a fu...
read it

Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)
This is the Proceedings of the 2017 ICML Workshop on Human Interpretabil...
read it

From Parity to Preferencebased Notions of Fairness in Classification
The adoption of automated, datadriven decision making in an ever expand...
read it

On Fairness, Diversity and Randomness in Algorithmic Decision Making
Consider a binary decision making process where a single machine learnin...
read it

Lost Relatives of the Gumbel Trick
The Gumbel trick is a method to sample from a discrete probability distr...
read it

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings
We examine a class of embeddings based on structured random matrices wit...
read it

Train and Test Tightness of LP Relaxations in Structured Prediction
Structured prediction is used in areas such as computer vision and natur...
read it

Clamping Improves TRW and Mean Field Approximations
We examine the effect of clamping variables for approximate inference in...
read it

Bethe Bounds and Approximating the Global Optimum
Inference in general Markov random fields (MRFs) is NPhard, though iden...
read it
Adrian Weller
verfied profile
Programme Director for Artificial Intelligence at The Alan Turing Institute since 2018, David MacKay Newton Research Fellow at Darwin College, Cambridge since 2017, Senior Research Fellow at Leverhulme Centre for the Future of Intelligence since 2016, Senior Research Fellow, Machine Learning at University of Cambridge since 2015, Turing Fellow at The Alan Turing Institute since 2016. Managing Director at Citadel from 19992004, Trader at Salomon Brothers from 19951999, Trader, desk head at Goldman Sachs from 19911995, Phd in Computer Science from 20082014.