14 papers
Learning-Theoretic Foundation for General Coded Computing: The Adversarial Setting
Parsa Moradi, Hanzaleh Akbarinodehi, Mohammad Ali Maddah-Ali
Adversarial workers pose a severe challenge in distributed computing systems by returning corrupted outputs that can substantially distort the recovered computations. Coded computi…
Manifold-Aware General Coded Computing for Straggler-Resilient Distributed Computing
Parsa Moradi, Mohammad Ali Maddah-Ali
Existing coded-computing designs do not explicitly exploit the intrinsic structure of the input data. In communication systems, statistical structure and redundancy are often remov…
Learning-Theoretic Foundation for General Coded Computing: The Straggler Setting
Parsa Moradi, Behrooz Tahmasebi, Mohammad Ali Maddah-Ali
Coded computing has emerged as a powerful paradigm for mitigating the impact of straggling workers in distributed computing systems. However, existing coded-computing schemes are p…
Learning from Acceptance: Cumulative Regret in the Game of Coding
Hanzaleh Akbari Nodehi, Parsa Moradi, Mohammad Ali Maddah-Ali
Classical coding-theoretic guarantees often rely on trust assumptions, such as requiring sufficiently many honest nodes compared with adversarial ones. These assumptions are diffic…
\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments
Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer +1
Decentralized machine learning often relies on outsourcing computations, such as gradient evaluations, to untrusted worker nodes. Existing robust aggregation methods can mitigate m…
Game of Coding for Vector-Valued Computations
Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer +1
Traditional coding theory guarantees valid decoding only if a minority of symbols are adversarially manipulated. In contrast, the game of coding framework ensures reliable decoding…
DReS: Dual Reconstruction Smoothing for Functional Regularization
Parsa Moradi, Tayyebeh Jahaninezhad, Hanzaleh Akbarinodehi +1
Smoothness is a key inductive bias in machine learning and is closely related to generalization. Existing smoothness-inducing methods typically rely either on explicit gradient reg…
Adversarial Robustness of Nonparametric Regression
Parsa Moradi, Hanzaleh Akabrinodehi, Mohammad Ali Maddah-Ali
In this paper, we investigate the adversarial robustness of nonparametric regression, a fundamental problem in machine learning, under the setting where an adversary can arbitraril…
General Coded Computing: Adversarial Settings
Parsa Moradi, Hanzaleh Akbarinodehi, Mohammad Ali Maddah-Ali
Conventional coded computing frameworks are predominantly tailored for structured computations, such as matrix multiplication and polynomial evaluation. Such tasks allow the reuse…
Game of Coding With an Unknown Adversary
Hanzaleh Akbarinodehi, Parsa Moradi, Mohammad Ali Maddah-Ali
Motivated by emerging decentralized applications, the \emph{game of coding} framework has been recently introduced to address scenarios where the adversary's control over coded sym…
General Coded Computing in a Probabilistic Straggler Regime
Parsa Moradi, Mohammad Ali Maddah-Ali
Coded computing has demonstrated promising results in addressing straggler resiliency in distributed computing systems. However, most coded computing schemes are designed for exact…
Private, Augmentation-Robust and Task-Agnostic Data Valuation Approach for Data Marketplace
Tayyebeh Jahani-Nezhad, Parsa Moradi, Mohammad Ali Maddah-Ali +1
Evaluating datasets in data marketplaces, where the buyer aim to purchase valuable data, is a critical challenge. In this paper, we introduce an innovative task-agnostic data valua…
Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework
Parsa Moradi, Behrooz Tahmasebi, Mohammad Ali Maddah-Ali
Coded computing has emerged as a promising framework for tackling significant challenges in large-scale distributed computing, including the presence of slow, faulty, or compromise…
NeRCC: Nested-Regression Coded Computing for Resilient Distributed Prediction Serving Systems
Parsa Moradi, Mohammad Ali Maddah-Ali
Resilience against stragglers is a critical element of prediction serving systems, tasked with executing inferences on input data for a pre-trained machine-learning model. In this…