|
I'm a second year Computer Science PhD student at Princeton University, advised by Elad Hazan. My research is focussed on interactive machine learning, and seeks to advance the theoretical understanding of reinforcement learning. I'm also invested in issues concerning privacy and fairness in machine learning. I did my bachelors at IIT Kanpur, where I worked on sketch-based algorithms for machine learning, and space lower bounds in the streaming model. I've also spent time at Microsoft Research in Redmond working on program synthesis. Email | CV | Google Scholar | Github | Blog |
|
|
|
|
We present an efficient and practical algorithm for the online prediction of discrete-time linear dynamical systems. Despite the non-convex optimization problem, our algorithm comes with provable guarantees: it has near-optimal regret bounds compared to the best LDS in hindsight, while overparameterizing the model by a small logarithmic factor. Our analysis brings together ideas from improper learning through convex relaxations, online regret minimization, and the spectral theory of Hankel matrices. |
|
We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal $O(\sqrt{T})$ regret bounds. In the full-information setting, our results demonstrate that $\epsilon$-differential privacy may be ensured for free. In particular, the regret bounds scale as $O\left(\sqrt{T}+\frac{1}{\epsilon}\right)$. For bandit linear optimization, and as a special case, for non-stochastic multi-armed bandits, the proposed algorithm achieves a regret of $O\left(\frac{1}{\epsilon}\sqrt{T}\right)$ while the previous best regret bound was $O\left(\frac{1}{\epsilon}T^{\frac{2}{3}}\right)$. |
|
We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. We give gradient-based methods that achieve optimal regret, which in turn guarantee convergence to equilibrium in this framework. |
|
|
Online Learning of Linear Dynamical Systems|
|
 |
|
|
|