no code implementations • 8 Jun 2022 • Serge Assaad, Carlton Downey, Rami Al-Rfou, Nigamaa Nayakanti, Ben Sapp
Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations.
no code implementations • NeurIPS 2018 • Siddarth Srinivasan, Carlton Downey, Byron Boots
Unlike classical graphical models, QGMs represent uncertainty with density matrices in complex Hilbert spaces.
1 code implementation • 30 Jan 2018 • Philip Andrew Mansfield, Quan Wang, Carlton Downey, Li Wan, Ignacio Lopez Moreno
We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space.
no code implementations • ICLR 2018 • Krzysztof Choromanski, Carlton Downey, Byron Boots
In this paper, we extend the theory of ORFs to Kernel Ridge Regression and show that ORFs can be used to obtain Orthogonal PSRNNs (OPSRNNs), which are smaller and faster than PSRNNs.
4 code implementations • 28 Oct 2017 • Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno
For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications.
Ranked #2 on Speaker Diarization on CALLHOME-109
no code implementations • NeurIPS 2017 • Carlton Downey, Ahmed Hefny, Boyue Li, Byron Boots, Geoffrey Gordon
We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems.
no code implementations • 14 Feb 2017 • Carlton Downey, Ahmed Hefny, Geoffrey Gordon
Unfortunately it is not obvious how to apply apply an EM style algorithm in the context of PSRs as the Log Likelihood is not well defined for all PSRs.
1 code implementation • 12 Feb 2017 • 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.
no code implementations • NeurIPS 2015 • Ahmed Hefny, Carlton Downey, Geoffrey Gordon
To address this problem, we present a new view of dynamical system learning: we show how to learn dynamical systems by solving a sequence of ordinary supervised learning problems, thereby allowing users to incorporate prior knowledge via standard techniques such as L1 regularization.
no code implementations • 9 Sep 2014 • Sashank Reddi, Ahmed Hefny, Carlton Downey, Avinava Dubey, Suvrit Sra
We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization.