1. Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions, AAAI 2021
    (with Zhe Feng, Guru Guruganesh, Aranyak Mehta, Abhishek Sethi)
  2. Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds, NeurIPS 2020
    (with Nick Harvey and Tasuku Soma)
  3. Optimal anytime regret with two experts, FOCS 2020
    (with Nick Harvey, Ed Perkins, Sikander Randhawa)
  4. The Vickrey Auction with a single duplicate bidder approximates the optimal revenue, EC 2019
    (with Hu Fu and Sikander Randhawa)
  5. Tight analyses for non-smooth stochastic gradient descent, COLT 2019
    (with Nick Harvey, Yaniv Plan, Sikander Randhawa)
  6. A new dog learns old tricks: RL finds classic algorithms, ICLR 2019
    (with William Kong, Aranyak Mehta, D. Sivakumar)
  7. Nearly-tight sample complexity bounds for learning mixtures of Gaussians via compression schemes, best paper at NeurIPS 2018
    (with Hassan Ashtiani, Shai Ben-David, Nick Harvey, Abbas Mehrabian, Yaniv Plan)
  8. Greedy and local ratio algorithms in the MapReduce model, SPAA 2018
    (with Paul Liu and Nick Harvey)
  9. Approximation schemes for covering and packing in the streaming model, in CCCG 2018
    (with Paul Liu and Robert Reiss)
  10. The value of information concealment, SODA 2018
    (with Hu Fu, Pinyan Lu, Zhihao Tang)
  11. Nearly-tight VC-dimension bounds for piecewise linear neural networks, COLT 2017
    (with Peter L. Bartlett, Nick Harvey, Abbas Mehrabian)
  12. Tight load balancing via randomized local search, IPDPS 2017
    (with Petra Berenbrink, Peter Kling, Abbas Mehrabian)
  13. A simple tool for bounding the deviation of random matrices on geometric sets, in Geometric Aspects of Functional Analysis
    (with Abbas Mehrabian, Yaniv Plan, and Roman Vershynin)
  14. Rainbow Hamilton cycles and lopsidependency, Discrete Mathematics
    (with Nick Harvey)