33 citations · 42 across the 13 of their papers we have counts for
13 papers
Accelerating Speculative Diffusions via Block Verification
Alexander Soen, Hisham Husain, Valentin De Bortoli +1
Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribu…
Seasoning Generative Models for a Generalization Aftertaste
Hisham Husain, Valentin De Bortoli, Richard Nock
The use of discriminators to train or fine-tune generative models has proven to be a rather successful framework. A notable example is Generative Adversarial Networks (GANs) that m…
Geometric Collaborative Filtering with Convergence
Hisham Husain, Julien Monteil
Latent variable collaborative filtering methods have been a standard approach to modelling user-click interactions due to their simplicity and effectiveness. However, there is limi…
Rejection via Learning Density Ratios
Alexander Soen, Hisham Husain, Philip Schulz +1
Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pi…
Confident Sinkhorn Allocation for Pseudo-Labeling
Vu Nguyen, Hisham Husain, Sachin Farfade +1
Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled data. It has been successfully applied to structured data, such as images and natur…
Distributionally Robust Bayesian Optimization with -divergences
Hisham Husain, Vu Nguyen, Anton van den Hengel
The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Op…
A Law of Robustness for Weight-bounded Neural Networks
Hisham Husain, Borja Balle
Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One me…
Regularized Policies are Reward Robust
Hisham Husain, Kamil Ciosek, Ryota Tomioka
Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overf…
Fair Densities via Boosting the Sufficient Statistics of Exponential Families
Alexander Soen, Hisham Husain, Richard Nock
We introduce a boosting algorithm to pre-process data for fairness. Starting from an initial fair but inaccurate distribution, our approach shifts towards better data fitting while…
Optimal Continual Learning has Perfect Memory and is NP-hard
Jeremias Knoblauch, Hisham Husain, Tom Diethe
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and…
Distributional Robustness with IPMs and links to Regularization and GANs
Hisham Husain
Robustness to adversarial attacks is an important concern due to the fragility of deep neural networks to small perturbations and has received an abundance of attention in recent y…
Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds
Hisham Husain, Richard Nock, Robert C. Williamson
Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence…
Integral Privacy for Sampling
Hisham Husain, Zac Cranko, Richard Nock
Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather pos…