Eric M. Fischer

Ph.D. Statistics with specialization in artificial intelligence

University of California Los Angeles

About Me

I am a first-year Ph.D. student specializing in artificial intelligence in the Department of Statistics at the University of California, Los Angeles. I carry out generative learning research on language models at the Center for Vision, Cognition, Learning, and Autonomy (VCLA) and am advised by Dr. Song-Chun Zhu.

I earned a Masters from the Department of Computer Science at UCLA and submitted a thesis “Deep Generative Classifier with Short Run Inference,” for which I built a deep generative classifier that utilizes short-run MCMC inference, Langevin dynamics, and backpropagation through time to achieve similar classification accuracy to an analogous convolutional neural network, but with the added benefits that it may generate data, may learn unsupervised from additional unlabeled data, and it exhibits robustness to adversarial attacks, due to the stochasticity of the Langevin equation and the top-down architecture of the underlying generator network.

Before my Masters, I worked as a Full Stack Software Engineer in the San Francisco bay area for over 2 years, most recently at NatureBox in Redwood City. I earned a Bachelors from the Department of Philosophy at UCLA, focusing my studies on first-order logic and language. Here is my Github.


  • Ph.D. Statistics, Present

    University of California, Los Angeles

  • M.S. Computer Science with Thesis, 2020

    University of California, Los Angeles

  • B.A. Philosophy, 2013

    University of California, Los Angeles


Book 1

I wrote two chapters and edited several others of “Statistical Models for Marr’s Paradigm”, a textbook authored by my Ph.D. …

Book 2

I edited several chapters of “Stochastic Grammars for Scene Parsing”, a textbook authored by my Ph.D. advisor Dr. Song-Chun …

Deep Generative Classifier with Short Run Inference

Deep generative classifier utilizes short-run Markov chain Monte Carlo inference, Langevin dynamics, and backpropagation through time …

Learning Multi-Layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference

Ran experiments for a short-run MCMC residual network that outperforms a variational autoencoder in terms of image reconstruction error …


Topology Adaptive Snakes Improve Mask Generation for Image Inpainting

T-snake deformable models, which can segment complex-shaped structures, improve generated masks passed to a GAN for image inpainting

Exact Sampling with Coupled Markov Chains and Swendsen-Wang Cluster Sampling of the Ising Model

Convergence analysis of exact sampling with Gibbs sampler and coupled Markov chains vs. cluster sampling with Swendsen-Wang algorithm

Implementation and Convergence Analysis of First-Order Optimization Methods for a CNN

Convergence analysis and Python implementations of SGD, SGD with momentum, SGD with Nesterov momentum, RMSprop, and Adam optimizers

Formulation of Variational Lower Bound and Application of VAE to MNIST Dataset

Formulation of the evidence lower bound (ELBO) for the variational autoencoder and an application to synthesizing binary images



Teaching Assistant

University of California, Los Angeles

Mar 2020 – Present Los Angeles, CA
Teaching assistant for courses: STATS 10 - Introduction to Statistical Reasoning, STATS 102 - Introduction to Monte Carlo Methods; Grader for courses: STATS 21 - Python and Other Technologies for Data Science

Graduate Student Researcher

Center for Vision, Cognition, Learning, and Autonomy

Dec 2018 – Present Los Angeles, CA
Perform generative learning research on language models with other lab members

Full Stack Software Engineer


Mar 2016 – Dec 2017 Redwood City, CA
Core contributor to new Flux/React web application after company added direct-to-consumer business; Led various projects including a payment processor migration, addition of Amazon payments, and a 2nd version of API

Software Engineer


Sep 2015 – Dec 2015 San Francisco, CA
Worked with Python, Ruby, and SQL code to construct internal data interfaces and tools

Wealth Advisor Associate

ClearPath Capital Partners

Jun 2014 – Sep 2013 San Francisco, CA
Passed Series 65 (Uniform Investment Adviser Law Exam) to acquire securities license as an investment advisor