activity
20102023
most citedPredicting Parameters in Deep Learning

697 citations · 1.5k across the 20 of their papers we have counts for

collaborators

21 papers

cs.LG2023

Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning

Patrick Emedom-Nnamdi, Abram L. Friesen, Bobak Shahriari +2

Standard approaches to sequential decision-making exploit an agent's ability to continually interact with its environment and improve its control policy. However, due to safety, et…

cs.CV2023★ 11 cited

Vision-Language Models as Success Detectors

Yuqing Du, Ksenia Konyushkova, Misha Denil +5

Detecting successful behaviour is crucial for training intelligent agents. As such, generalisable reward models are a prerequisite for agents that can learn to generalise their beh…

cs.AI2016

Building Machines That Learn and Think Like People

Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum +1

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks t…

cs.LG2015★ 227 cited

Neural Programmer-Interpreters

Scott Reed, Nando de Freitas

We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs. NPI has three learnable components:…

cs.LG2015★ 19 cited

ACDC: A Structured Efficient Linear Layer

Marcin Moczulski, Misha Denil, Jeremy Appleyard +1

The linear layer is one of the most pervasive modules in deep learning representations. However, it requires parameters and operations. These costs can be prohibi…

stat.ML2015★ 16 cited

Unbounded Bayesian Optimization via Regularization

Bobak Shahriari, Alexandre Bouchard-Côté, Nando de Freitas

Bayesian optimization has recently emerged as a popular and efficient tool for global optimization and hyperparameter tuning. Currently, the established Bayesian optimization pract…

cs.LG2014★ 15 cited

Deep Multi-Instance Transfer Learning

Dimitrios Kotzias, Misha Denil, Phil Blunsom +1

We present a new approach for transferring knowledge from groups to individuals that comprise them. We evaluate our method in text, by inferring the ratings of individual sentences…

cs.CL2014★ 85 cited

Extraction of Salient Sentences from Labelled Documents

Misha Denil, Alban Demiraj, Nando de Freitas

We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visual…

cs.CL2014★ 90 cited

Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network

Misha Denil, Alban Demiraj, Nal Kalchbrenner +2

Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retri…

stat.ML2014★ 2 cited

Distributed Parameter Estimation in Probabilistic Graphical Models

Yariv Dror Mizrahi, Misha Denil, Nando de Freitas

This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composi…

stat.ML2013★ 173 cited

Narrowing the Gap: Random Forests In Theory and In Practice

Misha Denil, David Matheson, Nando de Freitas

Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood. In this paper we contribute to this understanding in two…

stat.ML2013★ 1 cited

Linear and Parallel Learning of Markov Random Fields

Yariv Dror Mizrahi, Misha Denil, Nando de Freitas

We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields with untied parameters which is efficient for a large class of practical models. Ou…

cs.LG2013★ 697 cited

Predicting Parameters in Deep Learning

Misha Denil, Babak Shakibi, Laurent Dinh +2

We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accur…

stat.ML2013★ 10 cited

Exploiting correlation and budget constraints in Bayesian multi-armed bandit optimization

Matthew W. Hoffman, Bobak Shahriari, Nando de Freitas

We address the problem of finding the maximizer of a nonlinear smooth function, that can only be evaluated point-wise, subject to constraints on the number of permitted function ev…

stat.ML2013★ 36 cited

Consistency of Online Random Forests

Misha Denil, David Matheson, Nando de Freitas

As a testament to their success, the theory of random forests has long been outpaced by their application in practice. In this paper, we take a step towards narrowing this gap by p…

cs.AI2013★ 13 cited

Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (2012)

Nando de Freitas, Kevin Murphy

This is the Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, which was held on Catalina Island, CA August 14-18 2012.

stat.CO2012

Large-Flip Importance Sampling

Firas Hamze, Nando de Freitas

We propose a new Monte Carlo algorithm for complex discrete distributions. The algorithm is motivated by the N-Fold Way, which is an ingenious event-driven MCMC sampler that avoids…

stat.CO2012★ 1 cited

Intracluster Moves for Constrained Discrete-Space MCMC

Firas Hamze, Nando de Freitas

This paper addresses the problem of sampling from binary distributions with constraints. In particular, it proposes an MCMC method to draw samples from a distribution of the set of…

stat.ML2012★ 2 cited

Decentralized, Adaptive, Look-Ahead Particle Filtering

Mohamed Osama Ahmed, Pouyan T. Bibalan, Nando de Freitas +1

The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested s…

cs.LG2011★ 1 cited

A Machine Learning Perspective on Predictive Coding with PAQ

Byron Knoll, Nando de Freitas

PAQ8 is an open source lossless data compression algorithm that currently achieves the best compression rates on many benchmarks. This report presents a detailed description of PAQ…

cs.LG2010★ 91 cited

Portfolio Allocation for Bayesian Optimization

Eric Brochu, Matthew W. Hoffman, Nando de Freitas

Bayesian optimization with Gaussian processes has become an increasingly popular tool in the machine learning community. It is efficient and can be used when very little is known a…