Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Ravier, Robert"'
Autor:
Yanchenko, Anna K., Soltani, Mohammadreza, Ravier, Robert J., Mukherjee, Sayan, Tarokh, Vahid
Understanding the features learned by deep models is important from a model trust perspective, especially as deep systems are deployed in the real world. Most recent approaches for deep feature understanding or model explanation focus on highlighting
Externí odkaz:
http://arxiv.org/abs/2106.00110
In this paper, we propose a neural architecture search framework based on a similarity measure between some baseline tasks and a target task. We first define the notion of the task similarity based on the log-determinant of the Fisher Information mat
Externí odkaz:
http://arxiv.org/abs/2103.00241
The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge
Externí odkaz:
http://arxiv.org/abs/2010.13962
The approximation of both geodesic distances and shortest paths on point cloud sampled from an embedded submanifold $\mathcal{M}$ of Euclidean space has been a long-standing challenge in computational geometry. Given a sampling resolution parameter $
Externí odkaz:
http://arxiv.org/abs/2007.09885
Recent advances in time series classification have largely focused on methods that either employ deep learning or utilize other machine learning models for feature extraction. Though successful, their power often comes at the requirement of computati
Externí odkaz:
http://arxiv.org/abs/2007.06682
In this paper, we consider the problem of distributed online convex optimization, where a network of local agents aim to jointly optimize a convex function over a period of multiple time steps. The agents do not have any information about the future.
Externí odkaz:
http://arxiv.org/abs/1911.05050
In this paper, we consider the problem of distributed online convex optimization, where a group of agents collaborate to track the global minimizers of a sum of time-varying objective functions in an online manner. Specifically, we propose a novel di
Externí odkaz:
http://arxiv.org/abs/1911.05127
We develop a framework for estimating unknown partial differential equations from noisy data, using a deep learning approach. Given noisy samples of a solution to an unknown PDE, our method interpolates the samples using a neural network, and extract
Externí odkaz:
http://arxiv.org/abs/1910.10262
Autor:
Ravier, Robert, Tarokh, Vahid
Many techniques for online optimization problems involve making decisions based solely on presently available information: fewer works take advantage of potential predictions. In this paper, we discuss the problem of online convex optimization for pa
Externí odkaz:
http://arxiv.org/abs/1901.11500
Autor:
Ravier, Robert J.
Many algorithms for surface registration risk producing significant errors if surfaces are significantly nonisometric. Manifold learning has been shown to be effective at improving registration quality, using information from an entire collection of
Externí odkaz:
http://arxiv.org/abs/1812.10592