Search Results for author:
Found 16 papers, 6 papers with code
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
To do so, we investigate a simple self-training method based on expectation-maximization, which we call ReST$^{EM}$, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the model on these samples, and (3) repeat this process a few times.
Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documents
We argue for the utility of a human-in-the-loop approach in applications where high precision is required, but purely manual extraction is infeasible.
Modeling Content Creator Incentives on Algorithm-Curated Platforms
To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
We introduce repriorisation, a data-dependent reparameterisation which transforms a Bayesian neural network (BNN) posterior to a distribution whose KL divergence to the BNN prior vanishes as layer widths grow.
On component interactions in two-stage recommender systems
Thanks to their scalability, two-stage recommenders are used by many of today's largest online platforms, including YouTube, LinkedIn, and Pinterest.
Exploration in two-stage recommender systems
In this work, we focus on the complementary issue of exploration.
Infinite attention: NNGP and NTK for deep attention networks
There is a growing amount of literature on the relationship between wide neural networks (NNs) and Gaussian processes (GPs), identifying an equivalence between the two for a variety of NN architectures.
Exact posterior distributions of wide Bayesian neural networks
Recent work has shown that the prior over functions induced by a deep Bayesian neural network (BNN) behaves as a Gaussian process (GP) as the width of all layers becomes large.
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
Neural Tangents is a library designed to enable research into infinite-width neural networks.
Orthogonal Estimation of Wasserstein Distances
Wasserstein distances are increasingly used in a wide variety of applications in machine learning.
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning.
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
There is a previously identified equivalence between wide fully connected neural networks (FCNs) and Gaussian processes (GPs).
Variational Bayesian dropout: pitfalls and fixes
Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks.
Gaussian Process Behaviour in Wide Deep Neural Networks
Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties.
Variational Gaussian Dropout is not Bayesian
Gaussian multiplicative noise is commonly used as a stochastic regularisation technique in training of deterministic neural networks.
Concrete Dropout
Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks.
