Publications [Google Scholar]

* equal contribution authors. alphabetical authorship.

Papers

• Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
  I. Attias, G. K. Dziugaite, M. Haghifam , R. Livni, D. M. Roy
  Submitted, 2024

• Faster Differentially Private Convex Optimization via Second-Order Methods
  A. Ganesh, M. Haghifam , T. Steinke, A. Thakurta
  Advances in Neural Information Processing Systems (NeurIPS) 2023

• Why Is Public Pretraining Necessary for Private Model Training?
  A. Ganesh, M. Haghifam , M. Nasr, S. Oh, T. Steinke, O. Thakkar, A. Thakurta, L. Wang
  International Conference on Machine Learning (ICML), 2023

• Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization
  M. Haghifam* , B. Rodriguez-Galvez*, R. Thobaben, M. Skoglund, D. M. Roy, G. K. Dziugaite
  International Conference on Algorithmic Learning Theory (ALT), 2023

• Privacy-Preserving and Approximately Truthful Local Electricity Markets: A Differentially Private VCG Mechanism
  M. Hoseinpour, M. Hoseinpour, M. Haghifam , M. R. Haghifam
  IEEE Transactions on Smart Grid, 2023

• Understanding Generalization via Leave-One-Out Conditional Mutual Information
  M. Haghifam , S. Moran, D. M. Roy, G. K. Dziugaite
  International Symposium on Information Theory (ISIT), 2022

• On Streaming Codes With Unequal Error Protection
  M.Haghifam* , M. N. Krishnan*, A. Khisti, X. Zhu, W. Dan, J. Apostolopoulos
  IEEE Journal on Selected Areas in Information Theory, 2021

• Sequential Classification with Empirically Observed Statistics
  M. Haghifam , V. Y. F. Tan, A. Khisti
  IEEE Transactions on Information Theory, 2021

• Towards a Unified Information–Theoretic Framework for Generalization
  M. Haghifam , G. K. Dziugaite, S. Moran, D. M. Roy.
  Advances in Neural Information Processing Systems (NeurIPS), 2021 (Spotlight, <3% of submissions)

• Information-Theoretic Generalization Bounds for Stochastic Gradient Descent
  G. Neu, G. K. Dziugaite, M. Haghifam , D. M. Roy
  Annual Conference on Learning Theory (COLT), 2021

• Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
  M. Haghifam , J. Negrea, A. Khisti, D. M. Roy , G. K. Dziugaite,
  Advances in Neural Information Processing Systems (NeurIPS), 2020

• Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
  J. Negrea*, M. Haghifam* , G. K. Dziugaite, A. Khisti, D. M. Roy
  Advances in Neural Information Processing Systems (NeurIPS), 2019

• Joint Sum Rate And Error Probability Optimization: Finite Blocklength Analysis
  M. Haghifam , M. Robat Mili, B. Makki, M. Nasiri-Kenari, T. Svensson
  IEEE Wireless Communications Letters, 2017

Workshop Papers

• Sequential Classification with Empirically Observed Statistics
  M. Haghifam , V. Y. F. Tan, and A. Khisti
  IEEE Information Theory Workshop, 2019

• Streaming Codes with Unequal Error Protection against Burst Losses
  M. Haghifam , A. Badr, A. Khisti, X. Zhu, W. Dan and J. Apostolopoulos,
  The 29th Biennial Symposium on Communications, 2018

• On joint information and energy transfer in relay networks with an imperfect power amplifier \\[paper\\].
  M. Haghifam , B. Makki, M. Nasiri-Kenari, T. Svensson,
  IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), 2016

• State estimation in electric distribution networks in presence of distributed generation using the PMUs
  M. Haghifam , M. R. Haghifam, B. Safari Chabook,
  CIRED 2012