Search Results for author: Mohamed Osama Ahmed

Found 15 papers, 2 papers with code

Latent Bottlenecked Attentive Neural Processes

1 code implementation15 Nov 2022 Leo Feng, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

We demonstrate that LBANPs can trade-off the computational cost and performance according to the number of latent vectors.

Meta-Learning Multi-Armed Bandits

Towards Better Selective Classification

1 code implementation17 Jun 2022 Leo Feng, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Amir Abdi

We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset.

Classification

Stop Wasting My Gradients: Practical SVRG

no code implementations5 Nov 2015 Reza Babanezhad, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen

We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods.

Combining Bayesian Optimization and Lipschitz Optimization

no code implementations10 Oct 2018 Mohamed Osama Ahmed, Sharan Vaswani, Mark Schmidt

Indeed, in a particular setting, we prove that using the Lipschitz information yields the same or a better bound on the regret compared to using Bayesian optimization on its own.

Bayesian Optimization Thompson Sampling

StopWasting My Gradients: Practical SVRG

no code implementations NeurIPS 2015 Reza Harikandeh, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen

We present and analyze several strategies for improving the performance ofstochastic variance-reduced gradient (SVRG) methods.

Point Process Flows

no code implementations18 Oct 2019 Nazanin Mehrasa, Ruizhi Deng, Mohamed Osama Ahmed, Bo Chang, JiaWei He, Thibaut Durand, Marcus Brubaker, Greg Mori

Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature.

Point Processes

Monotonicity as a requirement and as a regularizer: efficient methods and applications

no code implementations29 Sep 2021 Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Greg Mori

We study the setting where risk minimization is performed over general classes of models and consider two cases where monotonicity is treated as either a requirement to be satisfied everywhere or a useful property.

Image Classification

Gumbel-Softmax Selective Networks

no code implementations19 Nov 2022 Mahmoud Salem, Mohamed Osama Ahmed, Frederick Tung, Gabriel Oliveira

This commonly encountered operational context calls for principled techniques for training ML models with the option to abstain from predicting when uncertain.

Meta Temporal Point Processes

no code implementations27 Jan 2023 Wonho Bae, Mohamed Osama Ahmed, Frederick Tung, Gabriel L. Oliveira

In this work, we propose to train TPPs in a meta learning framework, where each sequence is treated as a different task, via a novel framing of TPPs as neural processes (NPs).

Meta-Learning Point Processes

Memory Efficient Neural Processes via Constant Memory Attention Block

no code implementations23 May 2023 Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty.

Meta-Learning

Constant Memory Attention Block

no code implementations21 Jun 2023 Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

Modern foundation model architectures rely on attention mechanisms to effectively capture context.

Point Processes

Tree Cross Attention

no code implementations29 Sep 2023 Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

In this work, we propose Tree Cross Attention (TCA) - a module based on Cross Attention that only retrieves information from a logarithmic $\mathcal{O}(\log(N))$ number of tokens for performing inference.

Cannot find the paper you are looking for? You can Submit a new open access paper.