CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
We propose a simple but general framework for large-scale linear algebra problems in machine learning,
named CoLA (Compositional Linear Algebra).
By combining a linear operator abstraction with compositional dispatch rules,
CoLA automatically constructs memory and runtime efficient numerical algorithms.
-- 37th Conference on Neural Information Processing Systems
Topics: Numerical Methods, Machine Learning.
Simple and Fast Group Robustness by Automatic Feature Reweighting
We propose Automatic Feature Reweighting (AFR), an extremely simple and fast
method for updating a model to reduce its reliance on spurious features.
AFR retrains the last layer of a standard ERM-trained base model
with a weighted loss that emphasizes the examples where the ERM model
predicts poorly, automatically upweighting the minority group without
group labels. With this simple procedure, we improve upon the best
reported results among competing methods trained without spurious
attributes on several vision and natural language classification benchmarks,
using only a fraction of their compute.
-- 14th International Conference on Machine Learning
Topics: Group Robustness, Spurious Features, Last-layer
A Stable and Scalable Method for Solving Initial
Value PDEs with Neural Networks
We propose Neural-IVP, a method for approximating
solutions to high-dimensional PDEs though neural networks.
Our method is scalable, well-conditioned and runs in time linear
to the number of parameters in the neural network.
-- 11th Conference on Learning Representations
Topics: Inductive Biases, Partial Differential Equations, Numerical Linear
PAC-Bayes Compression Bounds So Tight That They
Can Explain Generalization
We develop a compression approach based on quantizing neural
network parameters in a random linear subspace profoundly
improving previous state-of-the-art generalization bounds and
showing how these tight bounds can help us understand the role of
model size, equivariance, and implicit biases in optimization.
-- 36th Conference on Neural Information Processing Systems (NeurIPS
Topics: Random Subspaces, Quantization, Equivariance,
Low-Precision Arithmetic for Fast Gaussian Processes
We study the different failure modes that can occur
when training GPs in half precision. To circumvent these failure
modes, we propose a multi-faceted approach involving conjugate
gradients with re-orthogonalization, mixed precision, and
preconditioning -- 38th Conference on Uncertainty in Artificial
Intelligence (UAI 2022).
Topics: Gaussian Processes, Quantization, Numerical Linear
Bias-Free Scalable Gaussian Processes via
We identify the biases introduced by approximate methods
and eliminate them via randomized truncation estimators
-- 38th International Conference on Machine Learning (ICML
Topics: Gaussian Processes, Russian-Roulette estimators,
Kernel Approximations, Numerical Linear Algebra.
Invertible Gaussian Reparameterization: Revisiting the
We introduce a family of continuous relaxations
that is more flexible, extensible and better performing than the
-- 34th Conference on Neural Information Processing Systems
Topics: Generative modeling, VAEs, Normalizing Flows,
Nowcasting with Google Trends
I propose an alternative kernel bandwidth selection
algorithm and exhibit what Google searches are relevant for
predicting unemployment, influenza outbreaks and violence spikes in Mexico.
The content is in English (past the acknowledgments) and relevant pages are:
4, 26, 36, 43, 48 -- Undergraduate Thesis.
Classifying webpages based on their menu
By modifying Word2Vec we recover an embedding that
helps to cluster clients based on their webpage's menu content -- Capstone Project.