arXiv subjects

Saurabh Khanna

Publications and source records attributed to Saurabh Khanna.

8 recordsLinked to original sources

arXiv2026

Picturing Perceptions: An Open-Source Toolkit to Uncover Bias in Humans and Machines

Bias in human judgment and artificial intelligence systems poses critical challenges across consequential domains like hiring, loans, and criminal justice. However, traditional bias measurement tools face fundamental limitations: they struggle to capture intersectional identities, cannot evaluate AI systems, lack grounding in demographic reality, and remain vulnerable to social desirability effects. We introduce PictoPercept, an open-source toolkit that measures bias through visual forced-choice comparisons grounded in population level benchmarks. Participants view pairs of normed facial photographs and assess who is more likely to have higher earnings, with selections compared against actual U.S. Bureau of Labor Statistics data. We validate PictoPercept with a nationally representative sample of 283 American adults and assess GPT-5, a mainstream generative model, using identical stimuli. Our study reveals three key findings: First, participants dramatically underestimate Asian American earnings despite this group having the highest actual earnings, while overestimating Latino male and White male earnings. Second, ingroup favoritism is not universal as White males show clear ingroup bias, but Asian participants actually underestimate their own group's earnings. Third, GPT-5 exhibits substantially stronger biases than humans, with stark systematic underestimation of all female groups. These findings suggest that PictoPercept enables unified bias assessment across human and AI systems while revealing systematic misperceptions that diverge from demographic reality.

cs.CY↗

arXiv2025

Invisible Languages of the LLM Universe

Large Language Models are trained on massive multilingual corpora, yet this abundance masks a profound crisis: of the world's 7,613 living languages, approximately 2,000 languages with millions of speakers remain effectively invisible in digital ecosystems. We propose a critical framework connecting empirical measurements of language vitality (real world demographic strength) and digitality (online presence) with postcolonial theory and epistemic injustice to explain why linguistic inequality in AI systems is not incidental but structural. Analyzing data across all documented human languages, we identify four categories: Strongholds (33%, high vitality and digitality), Digital Echoes (6%, high digitality despite declining vitality), Fading Voices (36%, low on both dimensions), and critically, Invisible Giants (27%, high vitality but near-zero digitality) - languages spoken by millions yet absent from the LLM universe. We demonstrate that these patterns reflect continuities from colonial-era linguistic hierarchies to contemporary AI development, constituting digital epistemic injustice. Our analysis reveals that English dominance in AI is not a technical necessity but an artifact of power structures that systematically exclude marginalized linguistic knowledge. We conclude with implications for decolonizing language technology and democratizing access to AI benefits.

cs.CL↗

arXiv2025

Knowing Unknowns in an Age of Information Overload

The technological revolution of the Internet has digitized the social, economic, political, and cultural activities of billions of humans. While researchers have been paying due attention to concerns of misinformation and bias, these obscure a much less researched and equally insidious problem - that of uncritically consuming incomplete information. The problem of incomplete information consumption stems from the very nature of explicitly ranked information on digital platforms, where our limited mental capacities leave us with little choice but to consume the tip of a pre-ranked information iceberg. This study makes two chief contributions. First, we leverage the context of internet search to propose an innovative metric that quantifies information completeness. For a given search query, this refers to the extent of the information spectrum that is observed during web browsing. We then validate this metric using 6.5 trillion search results extracted from daily search trends across 48 nations for one year. Second, we find causal evidence that awareness of information completeness while browsing the Internet reduces resistance to factual information, hence paving the way towards an open-minded and tolerant mindset.

cs.CY↗

arXiv2023

Who Provides the Largest Megaphone? The Role of Google News in Promoting Russian State-Affiliated News Sources

The Internet has not only digitized but also democratized information access across the globe. This gradual but path-breaking move to online information propagation has resulted in search engines playing an increasingly prominent role in shaping access to human knowledge. When an Internet user enters a query, the search engine sorts through the hundreds of billions of possible webpages to determine what to show. Google dominates the search engine market, with Google Search surpassing 80% market share globally every year of the last decade. Only in Russia and China do Google competitors claim more market share, with approximately 60% of Internet users in Russia preferring Yandex (compared to 40% in favor of Google) and more than 80% of China's Internet users accessing Baidu as of 2022. Notwithstanding this long-standing regional variation in Internet search providers, there is limited research showing how these providers compare in terms of propagating state-sponsored information. Our study fills this research gap by focusing on Russian cyberspace and examining how Google and Yandex's search algorithms rank content from Russian state-controlled media (hereon, RSM) outlets. This question is timely and of practical interest given widespread reports indicating that RSM outlets have actively engaged in promoting Kremlin propaganda in the lead-up to, and in the aftermath of, the Russian invasion of Ukraine in February 2022.

cs.IR↗

arXiv2021

On the Support Recovery of Jointly Sparse Gaussian Sources using Sparse Bayesian Learning

In this work, we provide non-asymptotic, probabilistic guarantees for successful recovery of the common nonzero support of jointly sparse Gaussian sources in the multiple measurement vector (MMV) problem. The support recovery problem is formulated as the marginalized maximum likelihood (or type-II ML) estimation of the variance hyperparameters of a joint sparsity inducing Gaussian prior on the source signals. We derive conditions under which the resulting nonconvex constrained optimization perfectly recovers the nonzero support of a joint-sparse Gaussian source ensemble with arbitrarily high probability. The support error probability decays exponentially with the number of MMVs at a rate that depends on the smallest restricted singular value and the nonnegative null space property of the self Khatri-Rao product of the sensing matrix. Our analysis confirms that nonzero supports of size as high as O($m^2$) are recoverable from $m$ measurements per sparse vector. Our derived sufficient conditions for support consistency of the proposed constrained type-II ML solution also guarantee the support consistency of any global solution of the multiple sparse Bayesian learning (M-SBL) optimization whose nonzero coefficients lie inside a bounded interval. For the case of noiseless measurements, we further show that a single MMV is sufficient for perfect recovery of the $k$-sparse support by M-SBL, provided all subsets of $k + 1$ columns of the sensing matrix are linearly independent.

cs.IT↗

arXiv2020

Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality

Granger causality is a widely-used criterion for analyzing interactions in large-scale networks. As most physical interactions are inherently nonlinear, we consider the problem of inferring the existence of pairwise Granger causality between nonlinearly interacting stochastic processes from their time series measurements. Our proposed approach relies on modeling the embedded nonlinearities in the measurements using a component-wise time series prediction model based on Statistical Recurrent Units (SRUs). We make a case that the network topology of Granger causal relations is directly inferrable from a structured sparse estimate of the internal parameters of the SRU networks trained to predict the processes$'$ time series measurements. We propose a variant of SRU, called economy-SRU, which, by design has considerably fewer trainable parameters, and therefore less prone to overfitting. The economy-SRU computes a low-dimensional sketch of its high-dimensional hidden state in the form of random projections to generate the feedback for its recurrent processing. Additionally, the internal weight parameters of the economy-SRU are strategically regularized in a group-wise manner to facilitate the proposed network in extracting meaningful predictive features that are highly time-localized to mimic real-world causal events. Extensive experiments are carried out to demonstrate that the proposed economy-SRU based time series prediction model outperforms the MLP, LSTM and attention-gated CNN-based time series models considered previously for inferring Granger causality.

cs.LG↗

arXiv2018

On the Restricted Isometry of the Columnwise Khatri-Rao Product

The columnwise Khatri-Rao product of two matrices is an important matrix type, reprising its role as a structured sensing matrix in many fundamental linear inverse problems. Robust signal recovery in such inverse problems is often contingent on proving the restricted isometry property (RIP) of a certain system matrix expressible as a Khatri-Rao product of two matrices. In this work, we analyze the RIP of a generic columnwise Khatri-Rao product matrix by deriving two upper bounds for its $k^{\text{th}}$ order Restricted Isometry Constant ($k$-RIC) for different values of $k$. The first RIC bound is computed in terms of the individual RICs of the input matrices participating in the Khatri-Rao product. The second RIC bound is probabilistic, and is specified in terms of the input matrix dimensions. We show that the Khatri-Rao product of a pair of $m \times n$ sized random matrices comprising independent and identically distributed subgaussian entries satisfies $k$-RIP with arbitrarily high probability, provided $m$ exceeds $O(k \log n)$. Our RIC bounds confirm that the Khatri-Rao product exhibits stronger restricted isometry compared to its constituent matrices for the same RIP order. The proposed RIC bounds are potentially useful in the sample complexity analysis of several sparse recovery problems.

cs.IT↗

arXiv2015

Decentralized Joint-Sparse Signal Recovery: A Sparse Bayesian Learning Approach

This work proposes a decentralized, iterative, Bayesian algorithm called CB-DSBL for in-network estimation of multiple jointly sparse vectors by a network of nodes, using noisy and underdetermined linear measurements. The proposed algorithm exploits the network wide joint sparsity of the un- known sparse vectors to recover them from significantly fewer number of local measurements compared to standalone sparse signal recovery schemes. To reduce the amount of inter-node communication and the associated overheads, the nodes exchange messages with only a small subset of their single hop neighbors. Under this communication scheme, we separately analyze the convergence of the underlying Alternating Directions Method of Multipliers (ADMM) iterations used in our proposed algorithm and establish its linear convergence rate. The findings from the convergence analysis of decentralized ADMM are used to accelerate the convergence of the proposed CB-DSBL algorithm. Using Monte Carlo simulations, we demonstrate the superior signal reconstruction as well as support recovery performance of our proposed algorithm compared to existing decentralized algorithms: DRL-1, DCOMP and DCSP.

cs.LG↗