I am an incoming doctoral student in the Computer Science department at the University of California San Diego starting fall 2021. Previously, I was a Research Fellow in the Machine Teaching Group at Max Planck Institute for Software Systems, where I had the great fortune to be advised by Dr. Adish Singla. I have also worked as a graduate student in the Department of Computer Science at Aalto Univerity (Finland) from September 2018 to August 2019. Prior to that, I completed my BSc in Mathematics and Computer Science (2013-2016) and MSc in Computer Science (2016-2018) from Chennai Mathematical Institute (CMI, India) under the supervision of Prof. K Venkata Subrahmanyam.
I am broadly interested in the theoretical aspects of machine learning. More specifically, I’m interested in statistical machine learning, algorithms, interactive learning, optimization, and theory of deep learning. I’m enthusiastic to explore and apply ideas from probability theory, analysis, differential geometry, and statistics to understand the computational and statistical efficiency of learning methods, and the extent to which machines can learn from data.
Contact: (username id) akk002 at ucsd dot edu
- Our paper on Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm is accepted at NeurIPS (2021)! :D
- Attended ICML’21 and COLT’21 conferences organized virtually.
- Our paper on The Teaching Dimension of Kernel Perceptrons is accepted at AISTATS (2021)! :D
- Attended NeurIPS’20 conference.
- Participated in Directions in ML: AutoML and Automating Algorithms Lecture series starting 28th July, 2020 by Microsoft Research which features talks by outstanding academics and domain experts.
Publications and Preprints
Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm
Akash Kumar, Yuxin Chen, Adish Singla.
Accepted in The 35th Conference on Neural Information Processing Systems (NeurIPS’21), 2021
The Teaching Dimension of Kernel Perceptrons
Akash Kumar, Hanqi Zhang, Adish Singla, Yuxin Chen.
Accepted in The 24th International Conference on Artificial Intelligence and Statistics (AISTATS’21), 2021
[ArXiv 2021], [Proc 2021]
Improved Certified Adversarial Lower Bound Using Adaptive Relaxations
Ongoing project on adversarial deep learning.
Natural Proofs Vs Derandomization
Project report completed as part of the Advanced Complexity course at Chennai Mathematical Institute.
I have been playing piano for a number of years and have been lucky to have some formal training to grade 2. Recently, I have picked up on Ukulele, which could be approximately thought of as a miniature version of a guiter with 4 strings.