Soham Phade
I am a Research Scientist in the AI Economist team at Salesforce Research. Prior to joining Salesforce, I graduated with a PhD degree from the EECS Department at UC Berkeley. You can reach me at:
Email: soham underscore phade at berkeley dot edu
Here is my curriculum vitae.
Projects
Interactive Learning with Smart Pricing for Optimal and Stable Allocations in Markets
We study the joint effect of pricing and recommendations in markets such as AirBnB, Uber, Doordash, Amazon, eBay, etc. We develop an efficient algorithm to minimize customer dissatisfaction and market instability in a repeated learning setting by integrating techniqes such as collaborative filtering, explore and exploit, and bidding protocols for optimal resource allocation.
Collaborators: YE Eringbas, K Ramchandran (UC Berkeley)
Building Enhanced Markets using AI
How to design assistive AI agents that learn individual user preferences, find top recommended actions out of several options for their user, bid opportunistically on behalf of the user in competing markets, be aware of the changing market conditions, and learn efficiently from past interactions? In this project we study these and other similar compelling questions.
Collaborators: YE Eringbas, L Butler, K Ramchandran (UC Berkeley)
Reinforcement Learning for Economic Policymaking
Deep reinforcement learning has shown promising results in games with a limited number of agents such as Chess, Go, Poker, etc. We develop methods to go beyond few agent settings and apply it to microeconomic simulations for finding general equilibria and optimal agent policies.
Collaborators: Stephan Zheng, Sunil Srinivasa, Stefano Ermon (Salesforce Research)
Behavioral Network Economics
As part of my PhD thesis, I focused on the role of behavioral models from psychology and decision theory (such as Cumulative Prospect Theory) in building efficient commercial systems that interact with humans.
Lottery-based optimal resource allocation
We develop the theory behind lotteries to incentivize people (eg. flight upgrades and middle-seat lotteries) and invent a lottery-based version of the TCP/IP protocol to design optimal lotteries.
Collaborators: V Anantharam (UC Berkeley)
About
In am interested in the design of networks and markets primarily from an economic and algorithmic point of view. My topics of interest include game theory, economics, behavioral psychology, decision theory, machine learning, reinforcement learning, and generative AI.
In Summer 2019, I interned as an Applied Scientist at Amazon Search Science and AI. Before joining UC Berkeley, I graduated from the Indian Institute of Technology, Bombay with a B.Tech. in Electrical Engineering with Honors and a Minor in Computer Science and Engineering.
Selected Publications
-
Learning in Games with Cumulative Prospect Theoretic Preferences.
Soham Phade and Venkat Anantharam
Dynamic Games and Applications (2021): 1-42
[link] [ArXiv] -
Optimal Resource Allocation over Networks via Lottery-Based Mechanisms.
Soham Phade and Venkat Anantharam
International Conference on Game Theory for Networks (pp 51-70), Springer, Cham (2019)
Best Paper Award at the 9th EAI International Conference on Game Theory for Networks, GameNets 2019, April 25-26, Paris.
[link] [ArXiv] [Short Video Presentation] -
On the Geometry of Nash and Correlated Equilibria with Cumulative Prospect Theoretic Preferences.
Soham Phade and Venkat Anantharam
Decision Analysis 16(2), 142-156 (2019)
[link] [ArXiv] -
A Distributed Boyle-Dykstra-Han Scheme.
Soham Phade and Vivek Borkar
SIAM journal on Optimization 27(3): 1880-1897 (2017)
[link]