40 citations · 151 across the 17 of their papers we have counts for
19 papers
Towards Faithful Data Selection: Statistical Limits and Scalable Algorithms
Ahmed Mehdi Inane, Mahdi Haghifam, Gintare Karolina Dziugaite +1
What does it mean to have an optimal data selection algorithm? Optimality is conventionally framed as finding a subset that minimizes the population error of the classifier trained…
Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
Shaddin Dughmi, Mahdi Haghifam, Yusuf Hakan Kalayci
Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execut…
The Distillation Game: Adaptive Evaluations & Efficient Defenses
Youssef Allouah, Mahdi Haghifam, Sanmi Koyejo +1
Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off t…
The Sample Complexity of Membership Inference and Privacy Auditing
Mahdi Haghifam, Adam Smith, Jonathan Ullman
A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a member of the training data or a…
On Traceability in Stochastic Convex Optimization
Sasha Voitovych, Mahdi Haghifam, Idan Attias +3
In this paper, we investigate the necessity of traceability for accurate learning in stochastic convex optimization (SCO) under geometries. Informally, we say a learning a…
Private Geometric Median
Mahdi Haghifam, Thomas Steinke, Jonathan Ullman
In this paper, we study differentially private (DP) algorithms for computing the geometric median (GM) of a dataset: Given points, in , the goal i…
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam +2
In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). We define memorization via the informati…
Faster Differentially Private Convex Optimization via Second-Order Methods
Arun Ganesh, Mahdi Haghifam, Thomas Steinke +1
Differentially private (stochastic) gradient descent is the workhorse of DP private machine learning in both the convex and non-convex settings. Without privacy constraints, second…
Why Is Public Pretraining Necessary for Private Model Training?
Arun Ganesh, Mahdi Haghifam, Milad Nasr +5
In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported with the use of pretraining on publicly…
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization
Mahdi Haghifam, Borja Rodríguez-Gálvez, Ragnar Thobaben +3
To date, no "information-theoretic" frameworks for reasoning about generalization error have been shown to establish minimax rates for gradient descent in the setting of stochastic…
Understanding Generalization via Leave-One-Out Conditional Mutual Information
Mahdi Haghifam, Shay Moran, Daniel M. Roy +1
We study the mutual information between (certain summaries of) the output of a learning algorithm and its training data, conditional on a supersample of i.i.d. data from…
Towards a Unified Information-Theoretic Framework for Generalization
Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran +1
In this work, we investigate the expressiveness of the "conditional mutual information" (CMI) framework of Steinke and Zakynthinou (2020) and the prospect of using it to provide a…
On the Information Complexity of Proper Learners for VC Classes in the Realizable Case
Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran +1
We provide a negative resolution to a conjecture of Steinke and Zakynthinou (2020a), by showing that their bound on the conditional mutual information (CMI) of proper learners of V…
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti +2
The information-theoretic framework of Russo and J. Zou (2016) and Xu and Raginsky (2017) provides bounds on the generalization error of a learning algorithm in terms of the mutual…
Sequential Classification with Empirically Observed Statistics
Mahdi Haghifam, Vincent Y. F. Tan, Ashish Khisti
Motivated by real-world machine learning applications, we consider a statistical classification task in a sequential setting where test samples arrive sequentially. In addition, th…
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite +2
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and recently extended by Bu, Zou, and Veeravalli…
Joint Sum Rate And Error Probability Optimization: Finite Blocklength Analysis
Mahdi Haghifam, Mohammad Robat Mili, Behrooz Makki +2
We study the tradeoff between the sum rate and the error probability in downlink of wireless networks. Using the recent results on the achievable rates of finite-length codewords,…
Wireless-powered relaying with finite block-length codes
Mahdi Haghifam, Behrooz Makki, Masoumeh Nasiri-Kenari +2
This paper studies the outage probability and the throughput of amplify-and-forward relay networks with wireless information and energy transfer. We use some recent results on fini…
On Wireless Energy and Information Transfer in Relay Networks
Mahdi Haghifam, Behrooz Makki, Masoumeh Nasiri-Kenari +1
This paper investigates the outage probability and the throughput of relay networks with wireless information and energy transfer where the relays harvest energy from the transmitt…