Ahmed Hefny — accepted AI-conference papers

2022

MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction

Balakrishnan Varadarajan, Ahmed Hefny, Avikalp Srivastava, Khaled S. Refaat, Nigamaa Nayakanti, Andre Cornman +5

ICRA 2022poster

Predicting the future behavior of road users is one of the most challenging and important problems in autonomous driving. Applying deep learning to this problem requires fusing heterogeneous world state in the form of rich perception signals and map information, and inferring highly multi-modal dist…

Cited by 366 Source ↗Scholar ↗

2018

Recurrent Predictive State Policy Networks

Ahmed Hefny, Zita Marinho, Wen Sun, Siddhartha Srinivasa, Geoffrey Gordon

ICML 2018oral

We introduce Recurrent Predictive State Policy(RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially ob-servable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a b…

Cited by 33 Source ↗PDF ↗code ↗Scholar ↗

2017

Predictive State Recurrent Neural Networks

Carlton Downey, Ahmed Hefny, Byron Boots, Geoffrey J. Gordon, Boyue Li

NeurIPS 2017poster

We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems. PSRNNs draw on insights from both Recurrent Neural Networks (RNNs) and Predictive State Representations (PSRs), and inherit advantages from both types of models. Like many…

Cited by 65 Source ↗PDF ↗code ↗Scholar ↗

2016

Stochastic Variance Reduction for Nonconvex Optimization

Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabas Poczos, Alex Smola

ICML 2016poster

We study nonconvex finite-sum problems and analyze stochastic variance reduced gradient (SVRG) methods for them. SVRG and related methods have recently surged into prominence for convex optimization given their edge over stochastic gradient descent (SGD); but their theoretical analysis almost exclus…

Cited by 738 Source ↗PDF ↗Scholar ↗

2015

On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants

Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabas Poczos, Alexander J Smola

NeurIPS 2015poster

We study optimization algorithms based on variance reduction for stochastic gradientdescent (SGD). Remarkable recent progress has been made in this directionthrough development of algorithms like SAG, SVRG, SAGA. These algorithmshave been shown to outperform SGD, both theoretically and empirically.…

Cited by 209 Source ↗PDF ↗Scholar ↗

2015

Supervised Learning for Dynamical System Learning

Ahmed Hefny, Carlton Downey, Geoffrey J. Gordon

NeurIPS 2015poster

Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoffbetween computational and statistical efficiency. Unfortunately, they can be difficult to use and extend in practice: e.g., they can make i…

Cited by 80 Source ↗PDF ↗Scholar ↗