Adam Block

Adam Block is a PhD student at MIT. He is advised by Alexander Rakhlin and his research is focused on machine learning. He works on designing provably effective algorithms in a variety of structured learning settings. Recently, he has been especially interested in online learning and sequential decision making, where the learner receives data sequentially and actively updates predictions and decisions as new information arrives, with applications to robotics, personalization, and much more.

Kaidi Cao

Kaidi Cao is a PhD student at Stanford University where he is advised by Jure Leskovec. Kaidi’s research focuses on data and computationally efficient machine learning. He is aiming to develop next-generation resource-efficient machine learning methods, including: 1) data-efficient deep learning through transferring knowledge from existing data or annotations, and 2) computationally efficient algorithms enabling learning from large-scale datasets.

Andrew Ilyas

Andrew Ilyas is studying EECS at MIT where he is advised by Aleksander Madry and Constantinos Daskalakis. Andrew’s research is in machine learning, with a focus on where errors, biases, or other features of the data-collection process (adversely) affect model predictions. In these settings, his research sets out to understand — both in theory and in practice — (a) why and how such effects arise; (b) how we might identify and mitigate them algorithmically; and (c) what benefits the resulting models confer.

Ce Jin

Ce Jin is a PhD student at MIT where he studies theoretical computer science. He is advised by Ryan Williams and Virginia Vassilevska Williams and his research focuses on fine-grained complexity theory. More specifically, he studies algorithms and conditional lower bounds for fundamental computational problems in graph theory, pattern matching, and combinatorial optimization.

Misha Khodak

Misha Khodak is a PhD student at Carnegie Mellon University studying theoretical machine learning. He is advised by Nina Balcan and Ameet Talwalkar and his research focuses on foundations and applications of machine learning, especially meta-learning and algorithm design. Misha focuses on machine learning methods for diverse tasks, including model compression, neural architecture search, the theory of unsupervised learning, and natural language processing. His work includes some of the first provable guarantees for gradient-based meta-learning and end-to-end guarantees for learning-augmented algorithms. Misha likes skiing, history books, and loose-leaf tea.

Marina Knittel

Marina Knittel is a student of computer science at the University of Maryland. She is advised by MohammadTaghi Hajiaghayi and John Dickerson and her research focuses on fair and parallel graph algorithms. Marina believes that with the advent of big data, we must ensure that vital decision-making systems keep pace with the growing scale of data and actively mitigate their own shortcomings. She studies algorithms on massive networks that achieve these two goals. For scalability, she studies classical graph problems in the Massively Parallel Computation (MPC) model. For bias mitigation, she studies fairness constraints in the context of partitioning problems such as clustering and allocation. In her spare time, she enjoys creative writing, Dungeons and Dragons, singing, and swing dancing.

Zhexiao Lin

Zhexiao Lin is a student at UC Berkeley advised by Peng Ding, Peter Bickel, and Fang Han. His research focuses on causal inference, graph-based methods, and econometrics. He explores two broad tracks: (i) how to measure treatment effects and assess effects of policy interventions using econometrics methods, and (ii) how to discover the intrinsic structure of large datasets in economics.

Surya Mathialagan

Surya Mathialagan is a PhD student in the CS theory group at MIT. She is advised by Vinod Vaikuntanathan and Virginia Vassilevska Williams, and her research focuses on fine-grained complexity and cryptography. She works on understanding the true runtimes of graph algorithms and is also interested in data-structure problems in cryptography and privacy. In her free time, Surya enjoys drawing, playing the guitar, and dancing.

Yifan Qiao

Yifan Qiao is a PhD student at UCLA advised by Harry Xu and Miryung Kim. His research focuses on building efficient systems for cloud computing and machine learning. Combining insights from ML algorithms, operating systems, and network stacks, Yifan designs and builds disaggregated cloud systems. In his spare time, he enjoys reading and playing Go.

Jacob Zavatone-Veth

Jacob Zavatone-Veth is a PhD student at Harvard University, advised by Cengiz Pehlevan. His research focuses on how networks of neurons can perform useful computations. He applies the tools of statistical physics to elucidate how artificial networks function, and builds models of biological networks to advance our understanding of the brain's algorithms. By understanding both biological intelligence and machine learning, he aims to create more naturally intelligent artificial systems. Jacob is half Swiss, but has never skied.

Yunkun Zhou

Yunkun Zhou is a student at Stanford University advised by Jacob Fox. His research explores extremal and additive combinatorics, specifically discrepancy theory. He is also generally interested in combinatorics and its applications in theoretical computer science.