Invited Presentations

• Challenges of the inconsistency regime: Novel debiasing methods for missing data models.
  IMS Young Mathematical Scientist Forum, November 20 – 23, 2023 (upcoming).

• Challenges of the inconsistency regime: Novel debiasing methods for missing data models.
  Online Causal Inference Seminar, October 24, 2023. (Youtube)

• Sudakov-Fernique post-AMP, and a new proof of the local convexity of the TAP free energy.
  Computational Complexity of Statistical Problems Workshop, MIT, June 14, 2023.
  (Youtube)

• Discussant for ‘‘A modern central limit theorem for the classical doubly robust estimator: variance inflation and beyond.’’
  Main speaker: Pragya Sur.
  International Seminar on Selective Inference, April 28, 2022.
  (Recording) (My discussion begins at minute 46)

• Sudakov-Fernique post-AMP, and a new proof of the local convexity of the TAP free energy.
  Computational Complexity of Statistical Inference Reunion, Simons Institute, December 13, 2021.

• Correlation-adjusted debiasing: Debiasing the Lasso with inaccurate covariate model.
  Neyman Seminar, Department of Statistics, University of California, Berkeley, December 1, 2021.
  (Recording)

• Correlation-adjusted debiasing: Debiasing the Lasso with inaccurate covariate model.
  Department Seminar, Department of Statistics, Wharton, University of Pennsylvania, October 27, 2021.

• The estimation error of general first order methods.
  Rigorous Evidence for Information-Computation Trade-offs, Simons Institute, October 27, 2021.
  (Youtube)

• Debiasing the Lasso with Inaccurate Precision Matrix.
  Youth in High Dimensions, ICTP, June 18, 2021.
  (Recording)

• The Lasso with general Gaussian designs with application to hypothesis testing.
  International Seminar on Selective Inference, September 10, 2020.
  (Recording) (Slides)

Contributed Oral Presentations

• Debiasing in missing data models with inaccurate nuisance parameters.
  Joint Statistical Meetings, August 9, 2023

• Debiasing in missing data models with inaccurate nuisance parameters.
  American Causal Inference Conference, May 24, 2023.

• Debiasing in missing data models with inaccurate nuisance parameters.
  Workshop on Computational-Statistical Interplay in Machine Learning, MIT, May 23, 2023.

• Debiasing in missing data models with inaccurate nuisance parameters.
  International Indian Statistical Association Conference, June 3, 2023.

• Correlation-adjusted debiasing: Debiasing the Lasso with inaccurate covariate model.
  Information Theory and Applications Workshop, February 14, 2023.

• Correlation-adjusted debiasing: Debiasing the Lasso with inaccurate covariate model.
  Meet the Fellows, Simons Institute, September 8, 2023.

• The Lasso with general Gaussian designs with application to hypothesis testing.
  Bernoulli-IMS One World Symposium, August 26, 2020.
  (Youtube) (Slides)

• Fundamental barriers to tractable estimation in high-dimensions.
  Joint Statistical Meetings, August 4, 2020.

• The estimation error of general first order methods.
  Conference on Learning Theory, July 9, 2020.
  (Youtube) (Slides)

• Mean field methods in high-dimensional statistics and nonconvex optimization.
  Online Open Probability School, Problem Session Leader. July 7 & 8, 2020.
  I led two problem solving sessions for a five lecture course given by Andrea Montanari. (Problem Sheet 1) (Problem Sheet 2)

• Fundamental barriers to tractable estimation in high-dimensions.
  CS Theory Seminar, Stanford University, April 22, 2020.
  (Slides)

• Fundamental barriers to estimation in high-dimensions.
  IT Forum, Stanford University, April 3, 2020.
  (Youtube) (Slides)