226 citations · 408 across the 9 of their papers we have counts for
11 papers
MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction
Balakrishnan Varadarajan, Ahmed Hefny, Avikalp Srivastava +8
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 het…
Recurrent Predictive State Policy Networks
Ahmed Hefny, Zita Marinho, Wen Sun +2
We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in par…
Predictive State Recurrent Neural Networks
Carlton Downey, Ahmed Hefny, Boyue Li +2
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 N…
Practical Learning of Predictive State Representations
Carlton Downey, Ahmed Hefny, Geoffrey Gordon
Over the past decade there has been considerable interest in spectral algorithms for learning Predictive State Representations (PSRs). Spectral algorithms have appealing theoretica…
An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems
Ahmed Hefny, Carlton Downey, Geoffrey J. Gordon
We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations…
Stochastic Variance Reduction for Nonconvex Optimization
Sashank J. Reddi, Ahmed Hefny, Suvrit Sra +2
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 c…
Rows vs. Columns: Randomized Kaczmarz or Gauss-Seidel for Ridge Regression
Ahmed Hefny, Deanna Needell, Aaditya Ramdas
The Kaczmarz and Gauss-Seidel methods aim to solve a linear system by iteratively refining the solution estimate; the fo…
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
Sashank J. Reddi, Ahmed Hefny, Suvrit Sra +2
We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development o…
Supervised Learning for Dynamical System Learning
Ahmed Hefny, Carlton Downey, Geoffrey Gordon
Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computatio…
Large-scale randomized-coordinate descent methods with non-separable linear constraints
Sashank Reddi, Ahmed Hefny, Carlton Downey +2
We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable…
A non-parametric mixture model for topic modeling over time
Avinava Dubey, Ahmed Hefny, Sinead Williamson +1
A single, stationary topic model such as latent Dirichlet allocation is inappropriate for modeling corpora that span long time periods, as the popularity of topics is likely to cha…