Spencer Frei

Department of Statistics
University of California, Los Angeles

Email: spencerfrei@ucla.edu
photo

I am a final-year PhD candidate in the Statistics department at UCLA and a member of the Statistical Machine Learning Lab led by Quanquan Gu.

Starting in August of 2021, I will be a postdoctoral fellow at UC Berkeley working with Peter Bartlett and Bin Yu as a part of the NSF/Simons program Collaboration on the Theoretical Foundations of Deep Learning.

Research Interests

My research is at the intersection of machine learning, statistics, and optimization. Particular topics of interest are the theory of deep learning and related topics; statistical learning theory; and applications of deep learning in domains like natural language understanding and audio.
2021
* 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 am currently a PhD candidate in the Statistics department at UCLA and a member of the Statistical Machine Learning Lab.  I am supervised by Ying Nian Wu from the Department of Statistics and Quanquan Gu from the Department of Computer Science. I completed my masters in mathematics at the University of British Columbia, Vancouver, in May 2015.  I was a member of the Probability Group, and Ed Perkins was my supervisor.  Before that, I completed my undergraduate degree in mathematics at McGill University in 2013.

You may find more information about me on my CV (last updated April 2021).

For 2020-2021, I have a UCLA Dissertation Year Fellowship and will not be teaching.

Past teaching positions:
Spring 2020: Stats 100C, Linear Models with Arash Amini.
Fall 2019: Stats 102C, Monte Carlo Methods with Qing Zhou.
Summer 2016, Session C: Stats 10, Intro Statistics with Juana Sanchez.
Summer 2016, Session A: Stats 10, Intro Statistics with Miles Chen.
Fall 2016: Stats 100A, Introduction to Probability Theory with Ying Nian Wu.
Winter 2016: Stats 100B, Introduction to Mathematical Statistics with Jessica Li.

Refereed Conference Publications

1. Difan Zou*, Spencer Frei*, and Quanquan Gu. Provable robustness of adversarial training for learning halfspaces with noise.
International Conference on Machine Learning (ICML), 2021.
arxiv:2104.09437.

2. Spencer Frei, Yuan Cao, and Quanquan Gu. Provable generalization of SGD-trained neural networks of any width in the presence of adversarial label noise.
International Conference on Machine Learning (ICML), 2021.
Appeared at the Theory of Overparameterized Machine Learning (TOPML2021) workshop.
arxiv:2101.01152.

3. Spencer Frei, Yuan Cao, and Quanquan Gu. Agnostic learning of halfspaces with gradient descent via soft margins.
International Conference on Machine Learning (ICML), 2021. Long talk.
arxiv:2010.00539.

4. Spencer Frei, Yuan Cao, and Quanquan Gu. Agnostic learning of a single neuron with gradient descent.
Advances in Neural Information Processing Systems (NeurIPS), 2020.
arxiv:2005.14426, conference paper.

5. Spencer Frei, Yuan Cao, and Quanquan Gu. Algorithm-dependent generalization bounds for overparameterized deep residual networks.
Advances in Neural Information Processing Systems (NeurIPS), 2019.
arxiv:1910.02934, conference paper.

Journal Publications

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

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

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

* denotes equal contribution.