arXiv subjects

Abhishek Kumar

Publications and source records attributed to Abhishek Kumar.

At least 127 records · Page 7Linked to original sources

arXiv2023

Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning

Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks. This paper proposes a novel method to reduce the parameters and FLOPs for computational efficiency in deep learning models. We introduce accuracy and efficiency coefficients to control the trade-off between the accuracy of the network and its computing efficiency. The proposed Rewarded meta-pruning algorithm trains a network to generate weights for a pruned model chosen based on the approximate parameters of the final model by controlling the interactions using a reward function. The reward function allows more control over the metrics of the final pruned model. Extensive experiments demonstrate superior performances of the proposed method over the state-of-the-art methods in pruning ResNet-50, MobileNetV1, and MobileNetV2 networks.

cs.CV↗

arXiv2022

Trial-Based Dominance Enables Non-Parametric Tests to Compare both the Speed and Accuracy of Stochastic Optimizers

Non-parametric tests can determine the better of two stochastic optimization algorithms when benchmarking results are ordinal, like the final fitness values of multiple trials. For many benchmarks, however, a trial can also terminate once it reaches a pre-specified target value. When only some trials reach the target value, two variables characterize a trial's outcome: the time it takes to reach the target value (or not) and its final fitness value. This paper describes a simple way to impose linear order on this two-variable trial data set so that traditional non-parametric methods can determine the better algorithm when neither dominates. We illustrate the method with the Mann-Whitney U-test. A simulation demonstrates that U-scores are much more effective than dominance when tasked with identifying the better of two algorithms. We test U-scores by having them determine the winners of the CEC 2022 Special Session and Competition on Real-Parameter Numerical Optimization.

cs.AI↗

arXiv2022

DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents

Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand, standard Variational Autoencoders (VAEs) typically have access to a low-dimensional latent space but exhibit poor sample quality. We present DiffuseVAE, a novel generative framework that integrates VAE within a diffusion model framework, and leverage this to design novel conditional parameterizations for diffusion models. We show that the resulting model equips diffusion models with a low-dimensional VAE inferred latent code which can be used for downstream tasks like controllable synthesis. The proposed method also improves upon the speed vs quality tradeoff exhibited in standard unconditional DDPM/DDIM models (for instance, FID of 16.47 vs 34.36 using a standard DDIM on the CelebA-HQ-128 benchmark using T=10 reverse process steps) without having explicitly trained for such an objective. Furthermore, the proposed model exhibits synthesis quality comparable to state-of-the-art models on standard image synthesis benchmarks like CIFAR-10 and CelebA-64 while outperforming most existing VAE-based methods. Lastly, we show that the proposed method exhibits inherent generalization to different types of noise in the conditioning signal. For reproducibility, our source code is publicly available at https://github.com/kpandey008/DiffuseVAE.

cs.LG↗

arXiv2022

Collective spin modes in Fermi liquids with spin-orbit coupling

A combination of spin-orbit coupling and electron-electron interaction gives rise to a new type of collective spin modes, which correspond to oscillations of magnetization even in the absence of the external magnetic field. We review recent progress in theoretical understanding and experimental observation of such modes, focusing on three examples of real-life systems: a two-dimensional electron gas with Rashba and/or Dresselhaus spin-orbit coupling, graphene with proximity-induced spin-orbit coupling, and the Dirac state on the surface of a three-dimensional topological insulator. This paper is dedicated to the 95th birthday of Professor Emmanuel I. Rashba.

cond-mat.str-el↗

arXiv2022

To Aggregate or Not? Learning with Separate Noisy Labels

The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e.g., via crowdsourcing). A typical way of using these separate labels is to first aggregate them into one and apply standard training methods. The literature has also studied extensively on effective aggregation approaches. This paper revisits this choice and aims to provide an answer to the question of whether one should aggregate separate noisy labels into single ones or use them separately as given. We theoretically analyze the performance of both approaches under the empirical risk minimization framework for a number of popular loss functions, including the ones designed specifically for the problem of learning with noisy labels. Our theorems conclude that label separation is preferred over label aggregation when the noise rates are high, or the number of labelers/annotations is insufficient. Extensive empirical results validate our conclusions.

cs.LG↗

arXiv2022

Impurity reveals distinct operational phases in quantum thermodynamic cycles

We analyze the effect of impurity on the work output and efficiency of quantum Otto and quantum Carnot heat cycles, modeled as a single quantum particle in an infinite square well (ISW) potential, which is the working substance. We solve this quantum mechanical system perturbatively up to first and second order in strength of the impurity for strong and weak coupling regimes, respectively. We derive the analytical expressions of work and efficiency for the strong coupling regime to the first order in the strength parameter. The threshold value of the strength parameter in weak coupling is obtained up to which the numerical result agrees with the perturbative result for a repulsive and attractive impurity. To our surprise, an embedded impurity unlocks new operational phases in the system, such as a quantum heat engine, quantum refrigerator, and quantum cold pump. In addition, the efficiency of the quantum Otto heat engine is seen to reach Carnot efficiency for some parameter regimes. The cooling power and coefficient of performance of the quantum refrigerator and quantum cold pump are non-trivially affected by the impurity.

quant-ph↗

arXiv2022

Enhancement of High Harmonic Generation in Bulk Floquet Systems

We formulate a theory of bulk optical current for a periodically driven system, which accounts for the mixing of external drive and laser field frequencies and, therefore, the broadening of the harmonic spectrum compared to the undriven system. We express the current in terms of Floquet-Bloch bands and their non-adiabatic Berry connection and curvature. Using this expression, we relate spatio-temporal symmetries of the driven model to selection rules for current harmonics. We illustrate the application of this theory by studying high harmonic generation in the periodically driven Su-Schrieffer-Heeger model. In the high frequency and low field amplitude limit, we find analytical expressions for current harmonics. We also calculate the current numerically beyond the high frequency limit and verify that when the drive breaks a temporal symmetry, harmonics forbidden in the undriven model become available. Moreover, we find significant enhancement in higher harmonics when the system is driven, even for low field amplitudes. Our work offers a unified Floquet approach to nonlinear optical properties of solids, which is useful for realistic calculations of high harmonic spectra of electronic systems subject to multiple periodic drives.

cond-mat.mes-hall↗

arXiv2022

Detection of field-free magnetization switching through thermoelectric effect in Ta/Pt/Co/Pt with significant spin-orbit torque and competing spin currents

Application of sufficient lateral current to a heavy metal (HM) can switch the perpendicular magnetization orientation of adjacent ferromagnetic layer (FM) through spin-orbit torques (SOTs). The choice of the HM and its arrangement plays a major role for the SOT induced magnetization switching in magnetic heterostructures. Here, in asymmetric Pt/Co/Pt heterostructures, anti-damping (AD) SOT prevails. Ta addition to this stack (Ta/Pt/Co/Pt) give rise to several compelling effects viz. competing spin currents (due to opposite spin-Hall angles of adjacent Ta and Pt layers), significant AD-SOT, thermoelectric effects (particularly, anomalous Nernst effect (ANE)), and enhanced perpendicular magnetic anisotropy. For this Ta/Pt/Co/Pt stack, the AD-SOT values are stabilized to that of the Pt/Co/Pt stack, which is significant than what is expected for a stack with competing spin currents. Current-induced field-free magnetization switching was absent in uniformly grown Ta/Pt/Co/Pt stack. It was observed that a thickness gradient is essential to assist the field-free magnetization switching in these heterostructures. Further, the thermoelectric effects are utilized to develop a technique to detect the field-free magnetization switching. This technique detects the second harmonic ANE signal as a reading mechanism. Using ANE symmetry with the applied current, the switching can be detected in a single current sweep which was corroborated to the conventional DC Hall method.

cond-mat.mes-hall↗

arXiv2022

Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications

Continual learning approaches help deep neural network models adapt and learn incrementally by trying to solve catastrophic forgetting. However, whether these existing approaches, applied traditionally to image-based tasks, work with the same efficacy to the sequential time series data generated by mobile or embedded sensing systems remains an unanswered question. To address this void, we conduct the first comprehensive empirical study that quantifies the performance of three predominant continual learning schemes (i.e., regularization, replay, and replay with examples) on six datasets from three mobile and embedded sensing applications in a range of scenarios having different learning complexities. More specifically, we implement an end-to-end continual learning framework on edge devices. Then we investigate the generalizability, trade-offs between performance, storage, computational costs, and memory footprint of different continual learning methods. Our findings suggest that replay with exemplars-based schemes such as iCaRL has the best performance trade-offs, even in complex scenarios, at the expense of some storage space (few MBs) for training examples (1% to 5%). We also demonstrate for the first time that it is feasible and practical to run continual learning on-device with a limited memory budget. In particular, the latency on two types of mobile and embedded devices suggests that both incremental learning time (few seconds - 4 minutes) and training time (1 - 75 minutes) across datasets are acceptable, as training could happen on the device when the embedded device is charging thereby ensuring complete data privacy. Finally, we present some guidelines for practitioners who want to apply a continual learning paradigm for mobile sensing tasks.

cs.LG↗

arXiv2022

Plagiarism deterrence for introductory programming

Plagiarism in introductory programming courses is an enormous challenge for both students and institutions. For students, relying on the work of others too early in their academic development can make it impossible to acquire necessary skills for independent success in the future. For institutions, widespread student cheating can dilute the quality of the educational experience being offered. Currently available solutions consider only pairwise comparisons between student submissions and focus on punitive deterrence. Our approach instead relies on a class-wide statistical characterization that can be clearly and securely shared with students via an intuitive new p-value representing independence of student effort. A pairwise, compression-based similarity detection algorithm captures relationships between assignments more accurately. An automated deterrence system is used to warn students that their behavior is being closely monitored. High-confidence instances are made directly available for instructor review using our open-source toolkit. An unbiased scoring system aids students and the instructor in understanding true independence of effort. Preliminary results indicate that the system can provide meaningful measurements of independence from week one, improving the efficacy of technical education.

cs.CY↗

arXiv2022

GridShift: A Faster Mode-seeking Algorithm for Image Segmentation and Object Tracking

In machine learning and computer vision, mean shift (MS) qualifies as one of the most popular mode-seeking algorithms used for clustering and image segmentation. It iteratively moves each data point to the weighted mean of its neighborhood data points. The computational cost required to find the neighbors of each data point is quadratic to the number of data points. Consequently, the vanilla MS appears to be very slow for large-scale datasets. To address this issue, we propose a mode-seeking algorithm called GridShift, with significant speedup and principally based on MS. To accelerate, GridShift employs a grid-based approach for neighbor search, which is linear in the number of data points. In addition, GridShift moves the active grid cells (grid cells associated with at least one data point) in place of data points towards the higher density, a step that provides more speedup. The runtime of GridShift is linear in the number of active grid cells and exponential in the number of features. Therefore, it is ideal for large-scale low-dimensional applications such as object tracking and image segmentation. Through extensive experiments, we showcase the superior performance of GridShift compared to other MS-based as well as state-of-the-art algorithms in terms of accuracy and runtime on benchmark datasets for image segmentation. Finally, we provide a new object-tracking algorithm based on GridShift and show promising results for object tracking compared to CamShift and meanshift++.

cs.CV↗

arXiv2022

Structural and electromechanical characterization of lead magnesium niobate-lead titanate (PMN-0.3PT) piezoceramic for energy harvesting applications

Efficient mechanical energy harvesting using the principle of piezoelectric effect demands specific material-property requirements. This includes a combination of large piezoelectric charge coefficient (dij), large elastic strain (εy), small elastic compliance (Sij), and small dielectric permittivity (\k{appa}ij). The present work undertakes structural, electrical, mechanical, and electromechanical characterization of pyrochlore-free lead magnesium niobate-lead titanate (1-x)[Pb(Mg(1/3)Nb(2/3)O3)]-xPbTiO3 at x = 0.3 or PMN-0.3PT, to estimate the above critical parameters for mechanical energy harvesting. Pyrochlore-free PMN-0.3PT ceramic with co-existing monoclinic (Pm and Cm) phases was synthesized using solid-state reaction method. Piezoelectric charge coefficient (d33), dielectric permittivity (\k{appa}33^T), elastic compliance (s33^E), and electromechanical coupling factor (k33), were estimated to be, 200 pC/N (approx), 1.06 (approx) x 10^-8 F/m, 13.16 (approx) x 10^-12 m2/N, and 0.54 (approx), respectively, using room temperature impedance measurement on a poled sample with specified dimensions (EN 50324-1:2002 and CEI/IEC 60483:1976). Polarization leakage due to transport of various charged defects was identified to be responsible for the reduced electromechanical properties compared to those reported for single crystals. Elastic strain (εy) vis-à-vis flexibility (fFOM) of the PMN-0.3PT was estimated to be 4.5 x 10-4. Energy harvesting under dynamic mechanical loading shows a maximum short-circuit current density, 95 nA/cm2, and an open-circuit electric field, 98 V/cm. With its impressive performance, PMN-0.3PT ceramic constitutes an important material for piezoelectric energy harvesting.

cond-mat.mtrl-sci↗

arXiv2022

Black Phosphorus n-type doping by Cu: a microscopic surface investigation

We study surface charge transfer doping of exfoliated black phosphorus (bP) flakes by copper using scanning tunneling microscopy (STM) and spectroscopy (STS) at room temperature. The tunneling spectra reveal a gap in correspondence of Cu islands, which is attributed to Coulomb blockade phenomena. Moreover, using line spectroscopic measurements across small copper islands, we exploit the potential of the local investigation, showing that the n-type doping effect of copper on bP is short-ranged. These experimental results are substantiated by first-principles simulations, which quantify the role of cluster size for an effective n-type doping of bP and explain the Coulomb blockade by an electronic decoupling of the topmost bP layer from the underlying layers driven by the copper cluster. Our results provide novel understanding, difficult to retrieve by transport measurements, of the doping of bP by copper, which appears promising for the implementation of ultra-sharp p-n junctions in bP.

cond-mat.mtrl-sci↗

arXiv2021

Solving Inverse Problems with NerfGANs

We introduce a novel framework for solving inverse problems using NeRF-style generative models. We are interested in the problem of 3-D scene reconstruction given a single 2-D image and known camera parameters. We show that naively optimizing the latent space leads to artifacts and poor novel view rendering. We attribute this problem to volume obstructions that are clear in the 3-D geometry and become visible in the renderings of novel views. We propose a novel radiance field regularization method to obtain better 3-D surfaces and improved novel views given single view observations. Our method naturally extends to general inverse problems including inpainting where one observes only partially a single view. We experimentally evaluate our method, achieving visual improvements and performance boosts over the baselines in a wide range of tasks. Our method achieves $30-40\%$ MSE reduction and $15-25\%$ reduction in LPIPS loss compared to the previous state of the art.

cs.CV↗

arXiv2021

When Creators Meet the Metaverse: A Survey on Computational Arts

The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity. This article conducts a comprehensive survey on computational arts, in which seven critical topics are relevant to the metaverse, describing novel artworks in blended virtual-physical realities. The topics first cover the building elements for the metaverse, e.g., virtual scenes and characters, auditory, textual elements. Next, several remarkable types of novel creations in the expanded horizons of metaverse cyberspace have been reflected, such as immersive arts, robotic arts, and other user-centric approaches fuelling contemporary creative outputs. Finally, we propose several research agendas: democratising computational arts, digital privacy, and safety for metaverse artists, ownership recognition for digital artworks, technological challenges, and so on. The survey also serves as introductory material for artists and metaverse technologists to begin creations in the realm of surrealistic cyberspace.

cs.CY↗

arXiv2021

Constrained Instance and Class Reweighting for Robust Learning under Label Noise

Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often degrades in the presence of noise. We propose a principled approach for tackling label noise with the aim of assigning importance weights to individual instances and class labels. Our method works by formulating a class of constrained optimization problems that yield simple closed form updates for these importance weights. The proposed optimization problems are solved per mini-batch which obviates the need of storing and updating the weights over the full dataset. Our optimization framework also provides a theoretical perspective on existing label smoothing heuristics for addressing label noise (such as label bootstrapping). We evaluate our method on several benchmark datasets and observe considerable performance gains in the presence of label noise.

cs.LG↗

arXiv2021

A thermodynamic probe of the topological phase transition in epitaxial graphene based Floquet topological insulator

One can use light to tune certain materials, from a trivial to a topological phase. A prime example of such materials, classified as Floquet topological insulators (FTI), is epitaxial graphene. In this paper, we probe the topological phase transition of an FTI via the efficiency and work output of quantum Otto and quantum Stirling heat engines. A maximum/minimum in the efficiency or work output invariably signals the phase transition point. Further, both engines' work output and efficiency are markedly robust against the polarization direction of light.

cond-mat.mes-hall↗

arXiv2021

All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda

Since the popularisation of the Internet in the 1990s, the cyberspace has kept evolving. We have created various computer-mediated virtual environments including social networks, video conferencing, virtual 3D worlds (e.g., VR Chat), augmented reality applications (e.g., Pokemon Go), and Non-Fungible Token Games (e.g., Upland). Such virtual environments, albeit non-perpetual and unconnected, have bought us various degrees of digital transformation. The term `metaverse' has been coined to further facilitate the digital transformation in every aspect of our physical lives. At the core of the metaverse stands the vision of an immersive Internet as a gigantic, unified, persistent, and shared realm. While the metaverse may seem futuristic, catalysed by emerging technologies such as Extended Reality, 5G, and Artificial Intelligence, the digital `big bang' of our cyberspace is not far away. This survey paper presents the first effort to offer a comprehensive framework that examines the latest metaverse development under the dimensions of state-of-the-art technologies and metaverse ecosystems, and illustrates the possibility of the digital `big bang'. First, technologies are the enablers that drive the transition from the current Internet to the metaverse. We thus examine eight enabling technologies rigorously - Extended Reality, User Interactivity (Human-Computer Interaction), Artificial Intelligence, Blockchain, Computer Vision, IoT and Robotics, Edge and Cloud computing, and Future Mobile Networks. In terms of applications, the metaverse ecosystem allows human users to live and play within a self-sustaining, persistent, and shared realm. Therefore, we discuss six user-centric factors -- Avatar, Content Creation, Virtual Economy, Social Acceptability, Security and Privacy, and Trust and Accountability. Finally, we propose a concrete research agenda for the development of the metaverse.

cs.CY↗