Adrian Weller

37

Papers

867

Total Citations

2

Affiliations

Affiliations

Alan Turing InstituteUniversity of Cambridge

Papers (37)

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

From Parity to Preference-based Notions of Fairness in Classification

NeurIPS 2017arXiv

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings

NeurIPS 2017arXiv

Uprooting and Rerooting Higher-Order Graphical Models

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Learning Personalized Decision Support Policies

Structural Causal 3D Reconstruction

Pairwise Similarity Learning is SimPLE

Orthogonal Over-Parameterized Training

Towards Principled Disentanglement for Domain Generalization

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

Diffused Redundancy in Pre-trained Representations

Quasi-Monte Carlo Graph Random Features

Use perturbations when learning from explanations

Certification of Distributional Individual Fairness

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Uprooting and Rerooting Graphical Models

Train and Test Tightness of LP Relaxations in Structured Prediction

Lost Relatives of the Gumbel Trick

Discovering Interpretable Representations for Both Deep Generative and Discriminative Models

Bucket Renormalization for Approximate Inference

Structured Evolution with Compact Architectures for Scalable Policy Optimization

Blind Justice: Fairness with Encrypted Sensitive Attributes

TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning

Unifying Orthogonal Monte Carlo Methods

Geometrically Coupled Monte Carlo Sampling

Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models

Ode to an ODE

Sub-Linear Memory: How to Make Performers SLiM

Iterative Teaching by Label Synthesis

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

Scalable Infomin Learning

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets

Chefs' Random Tables: Non-Trigonometric Random Features