9 citations · 18 across the 7 of their papers we have counts for
9 papers
Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
Ainesh Bakshi, Allen Liu, Ankur Moitra +1
Recently Chen and Poor initiated the study of learning mixtures of linear dynamical systems. While linear dynamical systems already have wide-ranging applications in modeling time-…
A New Approach to Learning Linear Dynamical Systems
Ainesh Bakshi, Allen Liu, Ankur Moitra +1
Linear dynamical systems are the foundational statistical model upon which control theory is built. Both the celebrated Kalman filter and the linear quadratic regulator require kno…
Approximating Nash Equilibrium in Random Graphical Games
Morris Yau
Computing Nash equilibrium in multi-agent games is a longstanding challenge at the interface of game theory and computer science. It is well known that a general normal form game i…
Kalman Filtering with Adversarial Corruptions
Sitan Chen, Frederic Koehler, Ankur Moitra +1
Here we revisit the classic problem of linear quadratic estimation, i.e. estimating the trajectory of a linear dynamical system from noisy measurements. The celebrated Kalman filte…
Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination
Sitan Chen, Frederic Koehler, Ankur Moitra +1
In this work we revisit two classic high-dimensional online learning problems, namely linear regression and contextual bandits, from the perspective of adversarial robustness. Exis…
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability
Sitan Chen, Frederic Koehler, Ankur Moitra +1
In this paper we revisit some classic problems on classification under misspecification. In particular, we study the problem of learning halfspaces under Massart noise with rate $η…
List Decodable Mean Estimation in Nearly Linear Time
Yeshwanth Cherapanamjeri, Sidhanth Mohanty, Morris Yau
Learning from data in the presence of outliers is a fundamental problem in statistics. Until recently, no computationally efficient algorithms were known to compute the mean of a h…
List Decodable Subspace Recovery
Prasad Raghavendra, Morris Yau
Learning from data in the presence of outliers is a fundamental problem in statistics. In this work, we study robust statistics in the presence of overwhelming outliers for the fun…
List Decodable Learning via Sum of Squares
Prasad Raghavendra, Morris Yau
In the list-decodable learning setup, an overwhelming majority (say a -fraction) of the input data consists of outliers and the goal of an algorithm is to output a small list…