Research publications

(in reverse chrononological order)

Preprints

• Inference in Multi-Layer Networks with Matrix-Valued Unknowns. [arXiv]
  (under review)
  P Pandit, M Sahraee-Ardakan, S Rangan, P Schniter, AK Fletcher

Journal articles

• Generalized Autoregressive Linear Models for Discrete High-dimensional Data. [IEEE Xplore]
  (2020 Journal on Selected Areas in Information Theory)
  P Pandit, M Sahraee-Ardakan, AA Amini, S Rangan, AK Fletcher

• Inference with Deep Generative Priors in High Dimensions. [arXiv]
  (2020 Journal on Selected Areas in Information Theory)
  P Pandit, M Sahraee-Ardakan, S Rangan, P Schniter, AK Fletcher

• Plug in estimation in high dimensional linear inverse problems a rigorous analysis. [paper]
  (2019 Journal of Statistical Mechanics: Theory and Experiment)
  AK Fletcher, P Pandit, S Rangan, S Sarkar, P Schniter

• Refinement of the Equilibrium of Public Goods Games over Networks: Efficiency and Effort of Specialized Equilibria. [paper]
  (2018 Journal of Mathematical Economics)
  P Pandit, AA Kulkarni

• A linear complementarity based characterization of the weighted independence number and the independent domination number in graphs. [paper]
  (2018 Discrete Applied Mathematics)
  P Pandit, AA Kulkarni

Conference articles

• Matrix inference and estimation in multi-layer models. [NeurIPS_proceedings]
  (2020 Advances in Neural Information Processing Systems (NeurIPS))
  P Pandit, M Sahraee-Ardakan, S Rangan, P Schniter, AK Fletcher

• Generalization error of GLMs in high dimensions. [arXiv]
  (2020 International Conference on Machine Learning (ICML))
  M Emami, M Sahraee-Ardakan, P Pandit, S Rangan, AK Fletcher

• High-Dimensional Analysis of Learning in Two-Layer Models. [poster]
  (2019 Conference on the Mathematical Theory of Deep Neural Networks (DeepMath))
  P Pandit, M Sahraee-Ardakan, AK Fletcher, S Rangan

• Asymptotics of MAP inference in Deep Networks. [paper, slides]
  (2019 International Symposium on Information Theory (ISIT))
  P Pandit, M Sahraee, S Rangan, AK Fletcher
  Winner of Jack K. Wolf Best Student Paper award

• Sparse Multivariate Bernoulli Processes in High Dimensions. [arXiv, paper, poster]
  (2019 Artificial Intelligence and Statistics (AISTATS))
  P Pandit, M Sahraee-Ardakan, AA Amini, S Rangan, AK Fletcher

• Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis. [paper]
  (2018 Neural Information Processing Systems (NeurIPS))
  AK Fletcher, P Pandit, S Rangan, S Sarkar, P Schniter

• Discount-based Pricing and Capacity Planning for EV Charging under Stochastic Demand. [paper, slides]
  (2018 Americal Controls Conference (ACC))
  P Pandit, S Coogan

• Non-constructive Lower Bounds for Binary Asymmetric Error Correcting Codes. [paper]
  (2017 IEEE National Conference on Communications (NCC))
  P Pandit, AA Kulkarni

• Structural segmentation of hindustani concert audio with posterior features. [paper]
  (2015 International Conferences on Accoustics Speech and Signal Processing (ICASSP))
  P Verma, TP Vinutha, P Pandit, P Rao

Theses

• Speaker Diarization for Broadcast News Audios (Masters Thesis)

• Automatic tempo identification from audio signal of bollywood music (Junior Thesis)