Joseph Gonzalez

Ashera: Neural Optimization Modulo Theories

Overview:

Ashera is a state-of-the-art Optimization Modulo Theory (OMT) solver, which explicitly targets a rising class of optimization problems such as multi-agent traveling salesman (mTSP) and multi-resource DAG scheduling. We excel at disjunctive problems which lead to well studied failure modes for ILP solvers exploiting both Logical Neighborhood Search and Neural Diving.

Logical Neighborhood Search decouples combinatorial search with convex optimization. For any feasible solution, Ashera performs convex optimization within...

Alpa: A Distributed System for Training and Serving Large Models

Alpa is a system for training and serving large-scale neural networks.

Scaling neural networks to hundreds of billions of parameters has enabled dramatic breakthroughs such as GPT-3, but training and serving these large-scale neural networks require complicated distributed system techniques. Alpa aims to automate large-scale distributed training and serving with just a few lines of code.

Code: https://github.com/alpa-projects/alpa

Active Visual Planning: Handling Uncertainty in Perception, Prediction, and Planning Pipelines

Abstract

When navigating complex multi-agent scenarios, humans not only reason about the uncertainty of their own perception, but also reason about the effect of their actions on their own perception. For example, a human driver at a blind intersection may inch forward to improve their visibility of oncoming traffic before deciding whether to proceed. This...

Factorized language representations with knowledge and logic

Knowledge and logical reasoning are essential constituents of spoken and written language. Despite the availability of more compact and accessible representations, such as knowledge graphs (KG) and logic forms, modern NLU technologies predominantly encapsulate knowledge and logical reasoning in vector representations along with other linguistic patterns. Despite its successes, this encapsulation erects barriers between NLU and symbolic technologies developed for knowledge representation and reasoning, which are inherently more transparent, robust, and scalable than their...

Learning Space Partitions for Path Planning

...

Graph Data Augmentation for Computer Systems

Graphs are the most common state representation for structured input problems including molecule property prediction, code representation learning and computer systems. Learning algorithms embed graph structures using graph neural networks (GNNs). However, many domains lack large training datasets due to the expense of acquiring samples; work by Mirhoseini et al. trained chip placement policies from a dataset of only 20 examples due to the complexity of designing new chips. In data-scarce settings, augmentation is widely used to improve generalization. Simple transformations like...

Next Generation Compiler Framework for Tensor Programs

More information on this project coming soon, please check back.