Spencer Frei

Simons Institute for the Theory of Computing
University of California, Berkeley

Email: frei@berkeley.edu
photo

I am a postdoctoral researcher at the Simons Institute for the Theory of Computing at UC Berkeley, hosted by Peter Bartlett and Bin Yu as a part of the NSF/Simons Collaboration on the Theoretical Foundations of Deep Learning. I'm interested in machine learning, statistics, and optimization, especially in deep learning theory.

Before coming to Berkeley, I completed my PhD in Statistics at UCLA under the supervision of Quanquan Gu and Ying Nian Wu. Prior to this, I completed a masters in mathematics at the University of British Columbia, Vancouver, where I was supervised by Ed Perkins. Before that, I completed my undergraduate degree in mathematics at McGill University.

My latest CV is here (last updated August 2021).


2021
* My paper on proxy convexity as a framework for neural network optimization was accepted at NeurIPS 2021.
* Two new preprints on arxiv: (1) Proxy convexity: a unified framework for the analysis of neural networks trained by gradient descent, and (2) Self training converts weak learners to strong learners in mixture models.
* I am reviewing for ICLR 2022.
* I am reviewing for the ICML 2021 workshop Overparameterization: Pitfalls and Opportunities (ICMLOPPO2021).
* Three recent papers accepted at ICML, including one as a long talk.
* New preprint on provable robustness of adversarial training for learning halfspaces with noise.
* I'm reviewing for NeurIPS 2021.
* I will be presenting recent work at TOPML2021 as a lightning talk, and at the SoCal ML Symposium as a spotlight talk.
* I'm giving a talk at the ETH Zurich Young Data Science Researcher Seminar on April 16th.
* I'm giving a talk at the Johns Hopkins University Machine Learning Seminar on April 2nd.
* I'm reviewing for the Theory of Overparameterized Machine Learning Workshop.
* I'm giving a talk at the Max-Planck-Insitute (MPI) MiS Machine Learning Seminar on March 11th.
* New preprint showing SGD-trained neural networks of any width generalize in the presence of adversarial label noise.
* I'm reviewing for ICML 2021.

2020
* New preprint on agnostic learning of halfspaces using gradient descent is now on arXiv.
* My single neuron paper was accepted at NeurIPS 2020.
* I received a Best Reviewer Award for ICML 2020.
* I will be attending the IDEAL Special Quarter on the Theory of Deep Learning hosted by TTIC/Northwestern for the fall quarter.
* I'm reviewing for AISTATS 2021.
* I've been awarded a Dissertation Year Fellowship by UCLA's Graduate Division.
* New preprint on agnostic PAC learning of a single neuron using gradient descent is now on arXiv.
* New paper accepted at Brain Structure and Function from work with researchers at UCLA School of Medicine.
* I'll be (remotely) working at Amazon's Alexa AI group for the summer as a research intern, working on natural language understanding.
* I'm reviewing for NeurIPS 2020.
* I'm reviewing for ICML 2020.

2019
* My paper with Yuan Cao and Quanquan Gu, "Algorithm-dependent Generalization Bounds for Overparameterized Deep Residual Networks", was accepted at NeurIPS 2019 (arXiv version, NeurIPS version).
I have a monthly radio show where I play music like house, techno, synth pop, new wave, post punk, disco, funk, and reggae.

My partner is a historian.

Preprints

Self-training converts weak learners to strong learners in mixture models.
Spencer Frei*, Difan Zou*, Zixiang Chen*, and Quanquan Gu.
Preprint, 2021.

Conference Publications

Proxy convexity: a unified framework for the analysis of neural networks trained by gradient descent.
Spencer Frei and Quanquan Gu.
Advances in Neural Information Processing Systems (NeurIPS), 2021.

Provable robustness of adversarial training for learning halfspaces with noise.
Difan Zou*, Spencer Frei*, and Quanquan Gu.
International Conference on Machine Learning (ICML), 2021.

Provable generalization of SGD-trained neural networks of any width in the presence of adversarial label noise.
Spencer Frei, Yuan Cao, and Quanquan Gu.
Appeared at the Theory of Overparameterized Machine Learning (TOPML2021) workshop.
International Conference on Machine Learning (ICML), 2021.

Agnostic learning of halfspaces with gradient descent via soft margins.
Spencer Frei, Yuan Cao, and Quanquan Gu.
International Conference on Machine Learning (ICML), 2021. Long talk.

Agnostic learning of a single neuron with gradient descent.
Spencer Frei, Yuan Cao, and Quanquan Gu.
Advances in Neural Information Processing Systems (NeurIPS), 2020.

Algorithm-dependent generalization bounds for overparameterized deep residual networks.
Spencer Frei, Yuan Cao, and Quanquan Gu.
Advances in Neural Information Processing Systems (NeurIPS), 2019.

Journal Publications

Hemodynamic latency is associated with reduced intelligence across the lifespan: an fMRI DCM study of aging, cerebrovascular integrity, and cognitive ability.
A.E. Anderson, M. Diaz-Santos, Spencer Frei et al.
Brain Structure and Function, 2020.

A lower bound for $p_c$ in range-$R$ bond percolation in two and three dimensions.
Spencer Frei and Edwin Perkins.
Electronic Journal of Probability 21(56), 2016.

On thermal resistance in concentric residential geothermal heat exchangers.
Spencer Frei, Kathryn Lockwood, Greg Stewart, Justin Boyer, and Burt S. Tilley.
Journal of Engineering Mathematics 86(1), 2014.

* denotes equal contribution.