sharpestats

Research

Papers, articles, and the code behind the blog.

Papers

Google Scholar ↗
2026

Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer

Yulun Wu, Sravan Kumar Ankireddy, Samuel Sharpe, Nikita Seleznev, Dehao Yuan, Hyeji Kim, Nam H. Nguyen

NeurIPS 2026

paper
2025

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning

Neha Kalibhat, Priyatham Kattakinda, Sumit Nawathe, Arman Zarei, Nikita Seleznev, Samuel Sharpe, Senthil Kumar, Soheil Feizi

CVPR 2025 · Workshops

paper
2024

A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers

Alex Stein, Samuel Sharpe, Doron Bergman, Senthil Kumar, C. Bayan Bruss, John Dickerson, Tom Goldstein, Micah Goldblum

Preprint · arXiv

paper
2023

Adapting Self-Supervised Representations to Multi-Domain Setups

Neha Kalibhat, Sam Sharpe, Jeremy Goodsitt, Bayan Bruss, Soheil Feizi

BMVC 2023

paper
2022

BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence

Isha Hameed, Samuel Sharpe, Daniel Barcklow, Justin Au-Yeung, Sahil Verma, Jocelyn Huang, Brian Barr, C. Bayan Bruss

KDD 2022 · Workshop on Machine Learning in Finance

paper
2021

Dynamic Customer Embeddings for Financial Service Applications

Nima Chitsazan, Samuel Sharpe, Dwipam Katariya, Qianyu Cheng, Karthik Rajasethupathy

ICML 2021 · Workshop on Representation Learning for Finance and e-Commerce Applications

paper
2020

Latent-CF: A Simple Baseline for Reverse Counterfactual Explanations

Rachana Balasubramanian, Sam Sharpe, Brian Barr, C. Bayan Bruss

NeurIPS 2020 · Workshop on Fair AI in Finance

paper
2019

Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities

Samuel Sharpe, Jin Yan, Fan Wu, Iddo Drori

CVPR 2019 · Language and Vision Workshop

papercode

Writing elsewhere

Capital One Tech Dynamic Customer Embeddings & Understanding Customer Intent How sequential recommendation and representation learning can be leveraged to model customer behavior. Capital One Tech Machine Learning for Temporal Data in Finance How machine learning methods are evolving to address the complex temporal and sequential elements of consumer financial data. MLB Technology MLB Pitch Classification A deep dive into recent enhancements of MLB's pitch classification system. MLB Technology An Introduction to Expected Weighted On-Base Average (xwOBA) An introduction to new baseball metrics derived from tracking data.

Projects on this blog

GitHub ↗

Injuries in Baseball: How (Self-)Exciting?

Modeling MLB player injury risk with self-exciting temporal point processes.

code

A/B Testing the Shift

Analyzing the effectiveness of the shift through propensity scores.

MVP Voter Model

MVP vote prediction model using a fused lasso formulated with a linear programming objective and constraints.

code

Making Baseball Slow Again

Analysis of the slowing pace of play in MLB.

code

Who Are the Best Romcom Actors?

Applying Regularized Adjusted Plus Minus (RAPM) to rate actors based on IMDb ratings.

code

Stealing Bases and Splitting the Rewards

Pitch-adjusted Swipe Rate Above Average: a mixed model that estimates pitcher, catcher, and runner stolen base skills.

code

Profiting Off the Nationals Presidents Race Puppet Masters

How to bet on the Presidents Race and make money using decision trees.

code