[AISTATS 2026]
Robust Estimation of a Sparse Linear Model - Provable Guarantees with Non-convexity
In this paper, we address the problem of sparse regression vector estimation in the presence of corrupted samples, with a particular …
[ICASSP 2025]
Partial Inference in Structured Prediction
In this paper, we examine the problem of partial inference in the context of structured prediction. Using a generative model approach, …
[ICASSP 2025]
Exact Solutions of the Inner Optimization Problem of Adversarial Robustness
We propose a robust framework that uses adversarially robust training to safeguard the ML models against perturbed testing data. Our …
[TMLR 2024]
A Theoretical Study of The Effects of Adversarial Attacks on Sparse Regression
This paper analyzes ℓ₁ regularized linear regression under the challenging scenario of having only adversarially corrupted data for …
[LoG 2023]
HEAL: Unlocking the Potential of Learning on Hypergraphs Enriched with Attributes and Layers
The paper aims to explore the untapped potential of hypergraphs by leveraging attribute-rich and multi-layered structures. The primary …
[PLOS ONE 2023]
Hypergraph Partitioning using Tensor Eigenvalue Decomposition
Hypergraphs have gained increasing attention in the machine learning community lately due to their superiority over graphs in capturing …
[J. Franklin Inst. 2022]
Identification of Errors-in-Variables ARX Models Using Modified Dynamic Iterative PCA
Identification of autoregressive models with exogenous input (ARX) is a classical problem in system identification. This article …
[MTNS 2020]
ARX Model Identification using Generalized Spectral Decomposition
Identification of autoregressive with exogenous inputs (ARX) models using spectral decomposition approach.
[Preprint]
Incorporating prior knowledge about structural constraints in model identification
Model identification techniques that leverage partial structural information to obtain better estimates of underlying models.
[ACODS 2020]
Identification of MISO systems in Minimal Realization Form
Identifying transfer functions of individual input channels in minimal realization form of Multi-Input Single Output (MISO) systems.
[I&ECR 2020]
Optimal Filtering and Residual Analysis in Errors-in-Variables Model Identification
Optimal filtering and residual generation method for errors-in-variables (EIV) scenario.
[NeurIPS 2019 Workshop]
Hypergraph Partitioning using Tensor Eigenvalue Decomposition
Hypergraph partitioning algorithm that doesn’t reduce hypergraph to a graph, thereby preserving all multi-way relationships.
[ICC 2019]
Identification of Output-Error (OE) Models using Generalized Spectral Decomposition
Novel two-step non-iterative framework to estimate delay and order using generalized spectral decomposition. Best Student Paper Award.
[I&ECR 2018]
Identification of Errors-in-Variables Models Using Dynamic Iterative Principal Component Analysis
Modified and faster version of identification algorithm for error in variables (EIV) systems.
[DYCOPS 2016]
Identification of Linear Dynamic Systems using Dynamic Iterative Principal Component Analysis
Identifying models from data with errors in both outputs and inputs; algorithm can estimate system order.
