
Simple HardwareEfficient Long Convolutions for Sequence Modeling
Elliot L. Epstein*, Dan Y. Fu*, Eric Nguyen, Armin W. Thomas, Michael Zhang, Tri Dao, Atri Rudra, Christopher Ré
ICML, 2023
arxiv /
code /
blog post /
What is the simplest architecture you can use to get good performance on sequence modeling with subquadratic compute scaling in the sequence length? State space models (SSMs) have high performance on long sequence modeling but require sophisticated initialization techniques and specialized implementations for high quality and runtime performance. This research studies whether directly learning long convolutions over the sequence can match SSMs in performance and efficiency.


Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors: comparison with expert subjective assessment
F Christiansen, Elliot L. Epstein, E Smedberg, Mans Akerlund, Kevin Smith, E Epstein
Ultrasound In Obstetrics & Gynaecology, 2021
arxiv /
This research develops a method to discriminate benign from malignant ovarian tumors based on transfer learning from a pretrained model on ImageNet. The model achieves an accuracy comparable to a human expert.

Internships
Work done during internships.


Student Researcher
Google
Oct. 2023 — Jan. 2024
Worked on an LLM based chatbot.


Software Engineering Intern
Google
Jun. 2023 — Sep. 2023


Intern, Quant and Data Group
EDF Trading
Apr. 2021 — Aug. 2021
 Developed a model in Python to predict the direction of the next trade of day ahead gas futures with over 70 percent
accuracy using LOB data and an ensemble of LSTM networks trained on multiple GPUs in the cloud.
 Built a web application to display real time predictions from neural network and random forest models to predict the
15minute ahead closing price of month ahead gas futures.
 Created an environment for trading using limit order book (LOB) data, and utilized a proximal policy optimization
reinforcement learning agent to create a trading strategy for month ahead gas futures.

Projects
These include coursework, side projects and unpublished research work.


Robust Domain Adaptation by Adversarial Training and Classification
Stanford CS224N: Natural Language Processing
Mar. 2022
This project extended a method to train a question answering model on out of distribution data by new data augmentation techniques and added a classifier module to determine if a question was answerable or not.
Work done in collaboration with Nicolas Ågnes.


Value Iteration for Markov Decision Processes
Stanford CME 307: Optimization
Mar. 2022
This project formulated an MDP problem as a linear program, a contraction result was proved.
Extensions of value and policy iteration were implemented and the convergence rate was analyzed, and the findings were empirically verifyed on a simple tictactoe implementation.


MultiFidelity Hamiltonian Monte Carlo
Stanford
Aug. 2020
poster /
Hamiltonian Monte Carlo improves upon standard MCMC when gradients of the probability distribution are available. However, for settings where the gradients are not available, such as for inverse modeling from physical simulations, these methods are not available.
This research shows the efficiency of a new algorithm, MultiFidelity Hamiltonian Monte Carlo, based on a Neural Network surrogate model for the gradient.
Work done as a research assistant with Eric Darve.


A review of the Article Gradient Descent Provably Optimizes overparameterized neural networks
ETH Zurich
Aug. 2020
paper /
This work theoretically studied convergence for a shallow neural network when trained with gradient descent.
By using a gradient flow argument, the dynamics of the predictions were directly analyzed rather than the weights.
Convergence was proved under the condition that the neural network is polynomially overparameterized and the least eigenvalue of a data dependent matrix is positive.
Work supervised by Arnulf Jentzen as part of my bachelor thesis at ETH Zurich.


Image Semantic Segmentation based on Deep Learning
Zhejiang University
Aug. 2019
Using Tensorflow, the MASKRCNN model is trained and evaluated on a new hand curated dataset.
Work done with Filip Christiansen as part of a research visit at Zhejiang University in Hangzhou, China.


Stanford University
Ph.D. in Computational and Mathematical Engineering
Stanford, United States
2021 — Present
GPA : 4.16/4.3


University of Oxford
MS in Mathematical and Computational Finance
Oxford, United Kingdom
2020 — 2021
 Stochastic Calculus
 Financial Statistics
 Advanced Monte Carlo Methods
 Financial Derivatives
 Quantitative Risk Management
 Algorithmic Trading
 Stochastic Control
 Asset Pricing
 Numerical Methods
 Financial Computing in C++
 Deep Learning


ETH Zurich
Exchange Student, Department of Mathematics
Zurich, Switzerland
2019 — 2020
 Probability Theory
 Programming Techniques for Scientific Simulations
 Electrodynamics
 Mathematical Foundations for Finance
 Geophysical Fluid Dynamics


KTH Royal Institute of Technology
BS in Engineering Physics
Stockholm, Sweden
2017 — 2020
GPA : 4.94/5.00
 Real Analysis
 Complex Analysis
 Quantum Mechanics
 Algorithms and Data Structures
 Probability and Statistics


Graduate Teaching Assistantships
Stanford, United States
 Financial Risk Analytics: MS&E 246 (Winter 2024)
 CME 218: Applied Data Science: CME 218 (Fall 2023)
Mentoring Stanford graduate students working on machine learning projects.
 Partial Differential Equations: CME 303 (Fall 2022)
A graduate class on partial differential equations.
 Machine Learning: CS 229 (Summer 2022)
Topics include: Supervised learning (deep learning), unsupervised learning, and reinforcement learning.

Blog
Short articles on various topics.

