Kumar Krishna Agrawal

graduate student at eecs, berkeley. previously research@google, math/cs at iit kharagpur

research: empirics, theory of learning algorithms in interactive, stochastic environments; building efficient, scalable real-world systems. some recent themes include:

  • measuring representation quality for model selection in self-supervised learning
  • offline reward modeling, reinforcement learning with limited, suboptimal data
  • algorithms for low-latency inference in ml pipelines
  • structured and compositional generative models (for code, images, audio)
previously, i've worked on fast, simple algorithms for off-policy robot learning, generative models for music, program synthesis.

opportunities: if you are at berkeley and interested in ml/systems research; please reach out!

about / teaching / writing / github / gscholar

teaching

Designing, Visualizing and Understanding Deep Neural Networks
fall 2022 @ ucberkeley

Introduction to Machine Learning
spring 2022, spring 2021 @ ucberkeley

Foundations of Machine Learning to Interact with a Dynamic World
fall 2021 @ ucberkeley

Depth First Learning : Learning to Understand Machine Learning
fellowship / whitepaper


(Template credits!)