no code implementations • 13 Aug 2014 • Panos Toulis, Edoardo M. Airoldi
Here, we introduce implicit stochastic gradient descent procedures, which involve parameter updates that are implicitly defined.
no code implementations • 21 Dec 2014 • Aviv Tamar, Panos Toulis, Shie Mannor, Edoardo M. Airoldi
In reinforcement learning, the TD($\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems.
no code implementations • 10 May 2015 • Panos Toulis, Dustin Tran, Edoardo M. Airoldi
For statistical efficiency, AI-SGD employs averaging of the iterates, which achieves the optimal Cram\'{e}r-Rao bound under strong convexity, i. e., it is an optimal unbiased estimator of the true parameter value.
1 code implementation • 22 Sep 2015 • Dustin Tran, Panos Toulis, Edoardo M. Airoldi
When the update is based on a noisy gradient, the stochastic approximation is known as standard stochastic gradient descent, which has been fundamental in modern applications with large data sets.
no code implementations • 4 Oct 2015 • Panos Toulis, Thibaut Horel, Edoardo M. Airoldi
Exact implementations of the proximal Robbins-Monro procedure are challenging, but we show that approximate implementations lead to procedures that are easy to implement, and still dominate classical procedures by achieving numerical stability, practically without tradeoffs.
no code implementations • 17 Oct 2017 • Jerry Chee, Panos Toulis
During the transient phase the procedure converges towards a region of interest, and during the stationary phase the procedure oscillates in that region, commonly around a single point.
1 code implementation • 27 Aug 2018 • Yi Ding, Panos Toulis
In this setting, we propose to screen out control units that have a weak dynamical relationship to the single treated unit before the model is fit.
Methodology
1 code implementation • 12 Aug 2019 • Panos Toulis
Randomization tests rely on simple data transformations and possess an appealing robustness property.
1 code implementation • 14 Jun 2021 • Y. Samuel Wang, Si Kai Lee, Panos Toulis, Mladen Kolar
We propose a residual randomization procedure designed for robust Lasso-based inference in the high-dimensional setting.
no code implementations • 11 Nov 2021 • Junhyung Lyle Kim, Panos Toulis, Anastasios Kyrillidis
Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training.