arXiv subjects

Krishna Acharya

Publications and source records attributed to Krishna Acharya.

11 recordsLinked to original sources

arXiv2026

Channel-Token Attention for Reliable Dynamic Spectrum Access under Bursty Primary-User Traffic

Dynamic spectrum access must coordinate secondary users under bursty primary-user activity while preserving packet reliability and delay. We present TACAN, a centralized policy that represents each channel as a token containing occupancy history and automatic-modulation-classification entropy; a context token supplies queue class, delay and user identity. A Transformer encoder is warm-started from an occupancy-greedy policy and refined with proximal policy optimization. The frozen policies were trained to maintain a channel assignment in every slot, including when queues were empty. We therefore replay them on held-out trajectories and distinguish standby assignment success from packet-present access and packet delivery. In a 20-channel network with 60 primary devices and 4 secondary users, TACAN achieves 92.53% +/- 0.47 packet-present access success, compared with 89.94% for Greedy and 83.53% for PPO+MLP. Its paired gain over Greedy is 2.59 points (parametric 95% CI 1.89-3.29), with wins in all five seeds; the exact two-sided sign-test value is 0.0625. The gain rises from 0.57 points at normal primary-user load to 7.67 points at extreme load. TACAN also reduces mean delivery delay from 1.208 to 1.123 slots and the conditional user-reliability gap from 9.69 to 3.15 points. Delivered packets per SU-slot remain arrival-limited (30.12% versus 30.11%), so no packet-throughput gain is claimed.

cs.NI↗

arXiv2026

Revealing the Atomic Structure of NiO/Ga$_{2}$O$_{3}$ Interfaces

NiO/Ga$_{2}$O$_{3}$ heterojunctions have garnered significant attention for use in power electronics due to the ultrawide bandgap and wafer-scale availability of Ga$_{2}$O$_{3}$ and the controllable p-type doping of NiO. However, the structure of NiO/Ga$_{2}$O$_{3}$ interfaces remains underexplored, largely due to the complexity of the junction between their dissimilar cubic and monoclinic crystal structures. Here we investigate the atomistic structure of the NiO/Ga$_{2}$O$_{3}$ interface for (100), (-201), and (001) oriented Ga$_{2}$O$_{3}$ substrates using aberration-corrected scanning transmission electron microscopy (STEM) in combination with interface modeling and image simulations. We evaluate the abruptness and consistency of the interfaces and compare them to calculated interface models, proposing precise atomic structures and assessing potential structural variation arising from complexity of the monoclinic Ga$_{2}$O$_{3}$ crystal structure. Our interface analysis supports increased focus on (100) oriented Ga$_{2}$O$_{3}$ as a candidate for fabricating high quality, low defect density NiO/Ga$_{2}$O$_{3}$ heterojunction devices. Importantly, we consider the effects of specimen thickness and 3D-to-2D projection during the STEM imaging process to differentiate such effects from real crystal variations. This work provides insight into the effect of substrate orientation on NiO film and interface quality, creating a pathway to improving heterojunction properties. It further highlights important considerations for interpretation of stability and interlayer phase formation in these interfaces, which is crucial for their integration into reliable and robust power electronic devices.

cond-mat.mtrl-sci↗

arXiv2025

Design and Implementation of a Multi-Purpose Low-Cost Hall-Effect Sensor Glove for Sign Language Recognition

Despite the prevalence of severe hearing loss affecting over 430 million people globally, access to sign language interpretation remains critically scarce, particularly in low-resource settings like Nepal. Assistive technologies divide into two flawed categories: prohibitively expensive commercial gloves (often exceeding \$3,000) or fragile research prototypes reliant on flex sensors that degrade rapidly under mechanical stress. This paper introduces a robust, cost-effective sign language recognition system tailored for the Nepali Sign Language (NSL) community. Departing from traditional resistive sensing, we implement a non-contact Hall-effect architecture that correlates magnetic field intensity with finger flexion, eliminating mechanical wear and signal drift. The system integrates 14 sensor nodes across the DIP, PIP, and MCP joints, augmented by an MPU6050 IMU for wrist orientation. An embedded Multi-Layer Perceptron, executed locally on an Arduino Mega, performs gesture classification, negating the need for cloud dependencies. With a Bill of Materials between \$80 and \$100, this solution is approximately 30 times more affordable than market alternatives. Validation trials across five subjects yielded 96\% accuracy on a fundamental NSL vocabulary. Stress testing confirmed that the Hall-effect configuration maintains signal fidelity over repeated cycles where traditional sensors fail. This study demonstrates that high-precision recognition is achievable through strategic engineering rather than premium components, offering a scalable pathway for deployment in Nepal's deaf schools.

cs.HC↗

arXiv2025

CNN-LSTM Hybrid Architecture for Over-the-Air Automatic Modulation Classification Using SDR

Automatic Modulation Classification (AMC) is a core technology for future wireless communication systems, enabling the identification of modulation schemes without prior knowledge. This capability is essential for applications in cognitive radio, spectrum monitoring, and intelligent communication networks. We propose an AMC system based on a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture, integrated with a Software Defined Radio (SDR) platform. The proposed architecture leverages CNNs for spatial feature extraction and LSTMs for capturing temporal dependencies, enabling efficient handling of complex, time-varying communication signals. The system's practical ability was demonstrated by identifying over-the-air (OTA) signals from a custom-built FM transmitter alongside other modulation schemes. The system was trained on a hybrid dataset combining the RadioML2018 dataset with a custom-generated dataset, featuring samples at Signal-to-Noise Ratios (SNRs) from 0 to 30dB. System performance was evaluated using accuracy, precision, recall, F1 score, and the Area Under the Receiver Operating Characteristic Curve (AUC-ROC). The optimized model achieved 93.48% accuracy, 93.53% precision, 93.48% recall, and an F1 score of 93.45%. The AUC-ROC analysis confirmed the model's discriminative power, even in noisy conditions. This paper's experimental results validate the effectiveness of the hybrid CNN-LSTM architecture for AMC, suggesting its potential application in adaptive spectrum management and advanced cognitive radio systems.

cs.LG↗

arXiv2025

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation

We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and inference on modest hardware. We evaluate GLoSS on three real-world Amazon review datasets: Beauty, Toys, and Sports, and find that it achieves state-of-the-art performance. Compared to traditional ID-based baselines, GLoSS improves Recall@5 by 33.3%, 52.8%, and 15.2%, and NDCG@5 by 30.0%, 42.6%, and 16.1%, respectively. It also outperforms LLM-based recommenders such as P5, GPT4Rec, LlamaRec and E4SRec with Recall@5 gains of 4.3%, 22.8%, and 29.5%. Additionally, user segment evaluations show that GLoSS performs particularly well for cold-start users in the Amazon Toys and Sports datasets, and benefits from longer user histories in Amazon Beauty dataset, demonstrating robustness across different levels of interaction lengths.

cs.IR↗

arXiv2025

Last-iterate Convergence for Symmetric, General-sum, $2 \times 2$ Games Under The Exponential Weights Dynamic

We conduct a comprehensive analysis of the discrete-time exponential-weights dynamic with a constant step size on all general-sum and symmetric $2 \times 2$ normal-form games, i.e. games with $2$ pure strategies per player, and where the ensuing payoff tuple is of the form $(A,A^\top)$ (where $A$ is the $2 \times 2$ payoff matrix corresponding to the first player). Such symmetric games commonly arise in real-world interactions between 'symmetric" agents who have identically defined utility functions -- such as Bertrand competition and multi-agent performative prediction, and display a rich multiplicity of equilibria despite the seemingly simple setting. Somewhat surprisingly, we show through a first-principles analysis that the exponential weights dynamic, which is popular in online learning, converges in the last iterate for such games regardless of initialization with an appropriately chosen step size. For certain games and/or initializations, we further show that the convergence rate is in fact exponential and holds for any step size. We illustrate our theory with extensive simulations and applications to the aforementioned game-theoretic interactions. In the case of multi-agent performative prediction, we formulate a new "mortgage competition" game between lenders (i.e. banks) who interact with a population of customers, and show that it fits into our framework.

cs.GT↗

arXiv2025

Improving Minimax Group Fairness in Sequential Recommendation

Training sequential recommenders such as SASRec with uniform sample weights achieves good overall performance but can fall short on specific user groups. One such example is popularity bias, where mainstream users receive better recommendations than niche content viewers. To improve recommendation quality across diverse user groups, we explore three Distributionally Robust Optimization(DRO) methods: Group DRO, Streaming DRO, and Conditional Value at Risk (CVaR) DRO. While Group and Streaming DRO rely on group annotations and struggle with users belonging to multiple groups, CVaR does not require such annotations and can naturally handle overlapping groups. In experiments on two real-world datasets, we show that the DRO methods outperform standard training, with CVaR delivering the best results. Additionally, we find that Group and Streaming DRO are sensitive to the choice of group used for loss computation. Our contributions include (i) a novel application of CVaR to recommenders, (ii) showing that the DRO methods improve group metrics as well as overall performance, and (iii) demonstrating CVaR's effectiveness in the practical scenario of intersecting user groups.

cs.IR↗

arXiv2024

Producers Equilibria and Dynamics in Engagement-Driven Recommender Systems

Online platforms such as YouTube, Instagram heavily rely on recommender systems to decide what content to present to users. Producers, in turn, often create content that is likely to be recommended to users and have users engage with it. To do so, producers try to align their content with the preferences of their targeted user base. In this work, we explore the equilibrium behavior of producers who are interested in maximizing user engagement. We study two variants of the content-serving rule for the platform's recommender system, and provide a structural characterization of producer behavior at equilibrium: namely, each producer chooses to focus on a single embedded feature. We further show that specialization, defined as different producers optimizing for distinct types of content, naturally emerges from the competition among producers trying to maximize user engagement. We provide a heuristic for computing equilibria of our engagement game, and evaluate it experimentally. We highlight i) the performance and convergence of our heuristic, ii) the degree of producer specialization, and iii) the impact of the content-serving rule on producer and user utilities at equilibrium and provide guidance on how to set the content-serving rule.

cs.GT↗

arXiv2024

Personalized Differential Privacy for Ridge Regression

The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requires to specify a uniform privacy level $\varepsilon$ that expresses the maximum privacy loss that each data point in the entire dataset is willing to tolerate. Yet, in practice, different data points often have different privacy requirements. Having to set one uniform privacy level is usually too restrictive, often forcing a learner to guarantee the stringent privacy requirement, at a large cost to accuracy. To overcome this limitation, we introduce our novel Personalized-DP Output Perturbation method (PDP-OP) that enables to train Ridge regression models with individual per data point privacy levels. We provide rigorous privacy proofs for our PDP-OP as well as accuracy guarantees for the resulting model. This work is the first to provide such theoretical accuracy guarantees when it comes to personalized DP in machine learning, whereas previous work only provided empirical evaluations. We empirically evaluate PDP-OP on synthetic and real datasets and with diverse privacy distributions. We show that by enabling each data point to specify their own privacy requirement, we can significantly improve the privacy-accuracy trade-offs in DP. We also show that PDP-OP outperforms the personalized privacy techniques of Jorgensen et al. (2015).

cs.LG↗

arXiv2023

Oracle Efficient Algorithms for Groupwise Regret

We study the problem of online prediction, in which at each time step $t$, an individual $x_t$ arrives, whose label we must predict. Each individual is associated with various groups, defined based on their features such as age, sex, race etc., which may intersect. Our goal is to make predictions that have regret guarantees not just overall but also simultaneously on each sub-sequence comprised of the members of any single group. Previous work such as [Blum & Lykouris] and [Lee et al] provide attractive regret guarantees for these problems; however, these are computationally intractable on large model classes. We show that a simple modification of the sleeping experts technique of [Blum & Lykouris] yields an efficient reduction to the well-understood problem of obtaining diminishing external regret absent group considerations. Our approach gives similar regret guarantees compared to [Blum & Lykouris]; however, we run in time linear in the number of groups, and are oracle-efficient in the hypothesis class. This in particular implies that our algorithm is efficient whenever the number of groups is polynomially bounded and the external-regret problem can be solved efficiently, an improvement on [Blum & Lykouris]'s stronger condition that the model class must be small. Our approach can handle online linear regression and online combinatorial optimization problems like online shortest paths. Beyond providing theoretical regret bounds, we evaluate this algorithm with an extensive set of experiments on synthetic data and on two real data sets -- Medical costs and the Adult income dataset, both instantiated with intersecting groups defined in terms of race, sex, and other demographic characteristics. We find that uniformly across groups, our algorithm gives substantial error improvements compared to running a standard online linear regression algorithm with no groupwise regret guarantees.

cs.LG↗

arXiv2022

Wealth Dynamics Over Generations: Analysis and Interventions

We present a stylized model with feedback loops for the evolution of a population's wealth over generations. Individuals have both talent and wealth: talent is a random variable distributed identically for everyone, but wealth is a random variable that is dependent on the population one is born into. Individuals then apply to a downstream agent, which we treat as a university throughout the paper (but could also represent an employer) who makes a decision about whether to admit them or not. The university does not directly observe talent or wealth, but rather a signal (representing e.g. a standardized test) that is a convex combination of both. The university knows the distributions from which an individual's type and wealth are drawn, and makes its decisions based on the posterior distribution of the applicant's characteristics conditional on their population and signal. Each population's wealth distribution at the next round then depends on the fraction of that population that was admitted by the university at the previous round. We study wealth dynamics in this model, and give conditions under which the dynamics have a single attracting fixed point (which implies population wealth inequality is transitory), and conditions under which it can have multiple attracting fixed points (which implies that population wealth inequality can be persistent). In the case in which there are multiple attracting fixed points, we study interventions aimed at eliminating or mitigating inequality, including increasing the capacity of the university to admit more people, aligning the signal generated by individuals with the preferences of the university, and making direct monetary transfers to the less wealthy population.

cs.GT↗