Author name cluster

Ashkan Panahi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Subgraph Federated Learning via Spectral Methods

Javad Aliakbari
Johan Oestman
Ashkan Panahi
Alexandre Graell i Amat

We consider the problem of federated learning (FL) with graph-structured data distributed across multiple clients. In particular, we address the common scenario of interconnected subgraphs, where interconnections between clients significantly influence the learning process. Existing approaches suffer from critical limitations, either requiring the exchange of sensitive node embeddings, thereby posing privacy risks, or relying on computationally-intensive steps, which hinders scalability. To tackle these challenges, we propose FedLap, a novel framework that leverages global structure information via Laplacian smoothing in the spectral domain to effectively capture inter-node dependencies while ensuring privacy and scalability. We provide a formal analysis of the privacy of FedLap, demonstrating that it preserves privacy. Notably, FedLap is the first subgraph FL scheme with strong privacy guarantees. Extensive experiments on benchmark datasets demonstrate that the proposed method achieves competitive or superior utility compared to existing techniques.

PDF Details

ICML Conference 2023 Conference Paper

Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework

Arman Rahbar
Ashkan Panahi
Morteza Haghir Chehreghani
Devdatt P. Dubhashi
Hamid Krim

We develop a novel theoretical framework for understating Optimal Transport (OT) schemes respecting a class structure. For this purpose, we propose a convex OT program with a sum-of-norms regularization term, which provably recovers the underlying class structure under geometric assumptions. Furthermore, we derive an accelerated proximal algorithm with a closed-form projection and proximal operator scheme, thereby affording a more scalable algorithm for computing optimal transport plans. We provide a novel argument for the uniqueness of the optimum even in the absence of strong convexity. Our experiments show that the new regularizer not only results in a better preservation of the class structure in the data but also yields additional robustness to the data geometry, compared to previous regularizers.

Details

AAAI Conference 2023 Conference Paper

Sharing Pattern Submodels for Prediction with Missing Values

Lena Stempfle
Ashkan Panahi
Fredrik D. Johansson

Missing values are unavoidable in many applications of machine learning and present challenges both during training and at test time. When variables are missing in recurring patterns, fitting separate pattern submodels have been proposed as a solution. However, fitting models independently does not make efficient use of all available data. Conversely, fitting a single shared model to the full data set relies on imputation which often leads to biased results when missingness depends on unobserved factors. We propose an alternative approach, called sharing pattern submodels (SPSM), which i) makes predictions that are robust to missing values at test time, ii) maintains or improves the predictive power of pattern submodels, and iii) has a short description, enabling improved interpretability. Parameter sharing is enforced through sparsity-inducing regularization which we prove leads to consistent estimation. Finally, we give conditions for when a sharing model is optimal, even when both missingness and the target outcome depend on unobserved variables. Classification and regression experiments on synthetic and real-world data sets demonstrate that our models achieve a favorable tradeoff between pattern specialization and information sharing.

PDF Details DOI

TCS Journal 2020 Journal Article

Accelerated proximal incremental algorithm schemes for non-strongly convex functions

Ashkan Panahi
Morteza Haghir Chehreghani
Devdatt Dubhashi

There have been a number of recent advances in accelerated gradient and proximal schemes for optimization of convex finite sum problems. Defazio introduced a simple accelerated scheme for incremental stochastic proximal algorithms inspired by gradient based methods like SAGA. He was able to prove O ( 1 / k ) convergence for non-smooth function but only under the assumption of strong convexity of component terms. We introduce a slight modification of his scheme, called MP-SAGA for which we can prove O ( 1 / k ) convergence without strong convexity, but for smooth functions. Numerical results show that our method has better or comparable convergence to Defazio's scheme, even for non-strongly convex functions. As important special cases, we also derive an accelerated schemes for a multi–class formulation of SVM as well as clustering based on the SON regularization. Finally, we introduce a simplification of Point–SAGA, called SP–SAGA for problems such as SON with large number of variables and sparse relation between variables and objective terms.

Details DOI

NeurIPS Conference 2017 Conference Paper

A Universal Analysis of Large-Scale Regularized Least Squares Solutions

Ashkan Panahi
Babak Hassibi

A problem that has been of recent interest in statistical inference, machine learning and signal processing is that of understanding the asymptotic behavior of regularized least squares solutions under random measurement matrices (or dictionaries). The Least Absolute Shrinkage and Selection Operator (LASSO or least-squares with $\ell_1$ regularization) is perhaps one of the most interesting examples. Precise expressions for the asymptotic performance of LASSO have been obtained for a number of different cases, in particular when the elements of the dictionary matrix are sampled independently from a Gaussian distribution. It has also been empirically observed that the resulting expressions remain valid when the entries of the dictionary matrix are independently sampled from certain non-Gaussian distributions. In this paper, we confirm these observations theoretically when the distribution is sub-Gaussian. We further generalize the previous expressions for a broader family of regularization functions and under milder conditions on the underlying random, possibly non-Gaussian, dictionary matrix. In particular, we establish the universality of the asymptotic statistics (e. g. , the average quadratic risk) of LASSO with non-Gaussian dictionaries.

PDF Details

ICML Conference 2017 Conference Paper

Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery

Ashkan Panahi
Devdatt P. Dubhashi
Fredrik D. Johansson
Chiranjib Bhattacharyya

Standard clustering methods such as K-means, Gaussian mixture models, and hierarchical clustering are beset by local minima, which are sometimes drastically suboptimal. Moreover the number of clusters K must be known in advance. The recently introduced the sum-of-norms (SON) or Clusterpath convex relaxation of k-means and hierarchical clustering shrinks cluster centroids toward one another and ensure a unique global minimizer. We give a scalable stochastic incremental algorithm based on proximal iterations to solve the SON problem with convergence guarantees. We also show that the algorithm recovers clusters under quite general conditions which have a similar form to the unifying proximity condition introduced in the approximation algorithms community (that covers paradigm cases such as Gaussian mixtures and planted partition models). We give experimental results to confirm that our algorithm scales much better than previous methods while producing clusters of comparable quality.

Details