Past Events

A Simple Convergence Proof for A Simple Convergence Proof Stochastic Approximation and Applications to Reinforcement Learning

Speaker: 

M. Vidyasagar

Organisers: 

Sandeep K Juneja

Time: 

Tuesday, 10 May 2022, 16:00 to 17:00

Venue: 

Since its invention by Robbins and Monro in 1951, the stochastic approximation (SA) algorithm has been a widely used tool for finding solutions of equations, or minimizing functions, with noisy measurements.

Shift, scale and restart smaller models to estimate larger ones: Agent based simulators in epidemiology

Speaker: 

Daksh Mittal

Organisers: 

Eeshan Modak

Time: 

Friday, 6 May 2022, 16:30 to 17:30

Venue: 

Agent-based simulators are a popular epidemiological modelling tool to study the impact of various non-pharmaceutical interventions in managing an evolving pandemic.

Sketching and Streaming Complexity of Constraint Satisfaction Problems

Speaker: 

Madhu Sudan

Organisers: 

Jaikumar Radhakrishnan

Time: 

Friday, 8 April 2022, 10:00 to 11:00

Venue: 

In this talk we will describe some of our recent work giving new upper and lower bounds on the approximability of constraint satisfaction problems (CSPs) in the streaming and sketching settings.

Pages