arXiv subjects

Saurabh Kumar

Publications and source records attributed to Saurabh Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2022

ScrawlD: A Dataset of Real World Ethereum Smart Contracts Labelled with Vulnerabilities

Smart contracts on Ethereum handle millions of U.S. Dollars and other financial assets. In the past, attackers have exploited smart contracts to steal these assets. The Ethereum community has developed plenty of tools to detect vulnerable smart contracts. However, there is no standardized data set to evaluate these existing tools, or any new tools developed. There is a need for an unbiased standard benchmark of real-world Ethereum smart contracts. We have created ScrawlD: an annotated data set of real-world smart contracts taken from the Ethereum network. The data set is labelled using 5 tools that detect various vulnerabilities in smart contracts, using majority voting.

cs.CR↗

arXiv2022

Probing TryOnGAN

TryOnGAN is a recent virtual try-on approach, which generates highly realistic images and outperforms most previous approaches. In this article, we reproduce the TryOnGAN implementation and probe it along diverse angles: impact of transfer learning, variants of conditioning image generation with poses and properties of latent space interpolation. Some of these facets have never been explored in literature earlier. We find that transfer helps training initially but gains are lost as models train longer and pose conditioning via concatenation performs better. The latent space self-disentangles the pose and the style features and enables style transfer across poses. Our code and models are available in open source.

cs.CV↗

arXiv2021

Predicting halo occupation and galaxy assembly bias with machine learning

Understanding the impact of halo properties beyond halo mass on the clustering of galaxies (namely galaxy assembly bias) remains a challenge for contemporary models of galaxy clustering. We explore the use of machine learning to predict the halo occupations and recover galaxy clustering and assembly bias in a semi-analytic galaxy formation model. For stellar-mass selected samples, we train a Random Forest algorithm on the number of central and satellite galaxies in each dark matter halo. With the predicted occupations, we create mock galaxy catalogues and measure the clustering and assembly bias. Using a range of halo and environment properties, we find that the machine learning predictions of the occupancy variations with secondary properties, galaxy clustering and assembly bias are all in excellent agreement with those of our target galaxy formation model. Internal halo properties are most important for the central galaxies prediction, while environment plays a critical role for the satellites. Our machine learning models are all provided in a usable format. We demonstrate that machine learning is a powerful tool for modelling the galaxy-halo connection, and can be used to create realistic mock galaxy catalogues which accurately recover the expected occupancy variations, galaxy clustering and galaxy assembly bias, imperative for cosmological analyses of upcoming surveys.

astro-ph.CO↗

arXiv2021

Characterizing the Gap Between Actor-Critic and Policy Gradient

Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper, we explain the gap between AC and PG methods by identifying the exact adjustment to the AC objective/gradient that recovers the true policy gradient of the cumulative reward objective (PG). Furthermore, by viewing the AC method as a two-player Stackelberg game between the actor and critic, we show that the Stackelberg policy gradient can be recovered as a special case of our more general analysis. Based on these results, we develop practical algorithms, Residual Actor-Critic and Stackelberg Actor-Critic, for estimating the correction between AC and PG and use these to modify the standard AC algorithm. Experiments on popular tabular and continuous environments show the proposed corrections can improve both the sample efficiency and final performance of existing AC methods.

cs.AI↗

arXiv2021

Laser-patterned multifunctional sensor array with graphene nanosheets as a smart biomonitoring fashion accessory

Biomonitoring wearable sensors based on two-dimensional nanomaterials have lately elicited keen research interest and potential for a new range of flexible nanoelectronic devices. Practical nanomaterial-based devices suited for real-world service, which have first-rate performance while being an attractive accessory, are still distant. We report a multifunctional flexible wearable sensor fabricated using an ultra-thin percolative layer of microwave exfoliated graphene nanosheets on laser-patterned gold circular inter-digitated electrodes for monitoring vital human physiological parameters. This Graphene on Laser-patterned Electrodes (GLE) sensor displays an ultra-high strain resolution of 0.024% and a record gauge factor of 6.3e7 and exceptional stability and repeatability in its operating range. The sensor was subjected to biomonitoring experiments like measurement of heart rate, breathing rate, body temperature, and hydration level, which are vital health parameters, especially considering the current pandemic scenario. The sensor also served in applications such as a pedometer, limb movement tracking, and control switch for human interaction. The innovative laser-etch process used to pattern gold thin-film electrodes and shapes, with the multifunctional incognizable graphene layer, provides a technique for integrating multiple sensors in a wearable fashion accessory. The reported work marks a giant leap from the conventional banal devices to a highly marketable multifunctional sensor array as a biomonitoring fashion accessory.

physics.app-ph↗

arXiv2020

Gradient Surgery for Multi-Task Learning

While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks to enable more efficient learning. However, the multi-task setting presents a number of optimization challenges, making it difficult to realize large efficiency gains compared to learning tasks independently. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. In this work, we identify a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develop a simple yet general approach for avoiding such interference between task gradients. We propose a form of gradient surgery that projects a task's gradient onto the normal plane of the gradient of any other task that has a conflicting gradient. On a series of challenging multi-task supervised and multi-task RL problems, this approach leads to substantial gains in efficiency and performance. Further, it is model-agnostic and can be combined with previously-proposed multi-task architectures for enhanced performance.

cs.LG↗

arXiv2020

Enhanced broadband Terahertz radiation from two colour laser pulse interaction with thin dielectric solid target in air

We report enhanced broadband Terahertz (THz) generation and detailed characterization from the interaction of femtosecond two colour laser pulses with thin transparent dielectric tape target in ambient air. The proposed source is easy to implement, exhibits excellent scalability with laser energy. Spectral characterization using Fourier transform spectrometer reveals yield enhancement of more than 150 % in the THz region of 0.1 - 10 THz with respect to conventional two-colour laser plasma source in ambient air. Further, the source spectrum extends up to 40 THz with an enhancement of flux > 30 %. Experimental results, well supported with two-dimensional particle-in-cell simulations establishes that the transient photo-current produced by the asymmetric laser pulse interaction with air plasma as well as near solid density plasma formed on the tape surface is responsible for the enhanced terahertz generation. The source will be useful for the multidisciplinary activities and ongoing applications of the laboratory-based terahertz sources.

physics.optics↗

arXiv2020

Reduced Graphene Oxide Tattoo as Wearable Proximity Sensor

The human body is punctuated with wide array of sensory systems that provide a high evolutionary advantage by facilitating formation of a detailed picture of the immediate surroundings. The sensors range across a wide spectrum, acquiring input from non-contact audio-visual means to contact based input via pressure and temperature. The ambit of sensing can be extended further by imparting the body with increased non-contact sensing capability through the phenomenon of electrostatics. Here we present graphene-based tattoo sensor for proximity sensing, employing the principle of electrostatic gating. The sensor shows a remarkable change in resistance upon exposure to objects surrounded with static charge on them. Compared to prior work in this field, the sensor has demonstrated the highest recorded proximity detection range of 20 cm. It is ultra-thin, highly skin conformal and comes with a facile transfer process such that it can be tattooed on highly curvilinear rough substrates like the human skin, unlike other graphene-based proximity sensors reported before. Present work details the operation of wearable proximity sensor while exploring the effect of mounting body on the working mechanism. A possible role of the sensor as an alerting system against unwarranted contact with objects in public places especially during the current SARS-CoV-2 pandemic has also been explored in the form of an LED bracelet whose color is controlled by the proximity sensor attached to it.

cs.HC↗

arXiv2020

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this problem is to train agents with manually specified variation in the training task or environment. However, this may be infeasible in practical situations, either because making perturbations is not possible, or because it is unclear how to choose suitable perturbation strategies without sacrificing performance. The key insight of this work is that learning diverse behaviors for accomplishing a task can directly lead to behavior that generalizes to varying environments, without needing to perform explicit perturbations during training. By identifying multiple solutions for the task in a single environment during training, our approach can generalize to new situations by abandoning solutions that are no longer effective and adopting those that are. We theoretically characterize a robustness set of environments that arises from our algorithm and empirically find that our diversity-driven approach can extrapolate to various changes in the environment and task.

cs.LG↗

arXiv2020

3D-NVS: A 3D Supervision Approach for Next View Selection

We present a classification based approach for the next best view selection and show how we can plausibly obtain a supervisory signal for this task. The proposed approach is end-to-end trainable and aims to get the best possible 3D reconstruction quality with a pair of passively acquired 2D views. The proposed model consists of two stages: a classifier and a reconstructor network trained jointly via the indirect 3D supervision from ground truth voxels. While testing, the proposed method assumes no prior knowledge of the underlying 3D shape for selecting the next best view. We demonstrate the proposed method's effectiveness via detailed experiments on synthetic and real images and show how it provides improved reconstruction quality than the existing state of the art 3D reconstruction and the next best view prediction techniques.

cs.CV↗

arXiv2020

Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification

Real-world scenarios pose several challenges to deep learning based computer vision techniques despite their tremendous success in research. Deeper models provide better performance, but are challenging to deploy and knowledge distillation allows us to train smaller models with minimal loss in performance. The model also has to deal with open set samples from classes outside the ones it was trained on and should be able to identify them as unknown samples while classifying the known ones correctly. Finally, most existing image recognition research focuses only on using two-dimensional snapshots of the real world three-dimensional objects. In this work, we aim to bridge these three research fields, which have been developed independently until now, despite being deeply interrelated. We propose a joint Knowledge Distillation and Open Set recognition training methodology for three-dimensional object recognition. We demonstrate the effectiveness of the proposed method via various experiments on how it allows us to obtain a much smaller model, which takes a minimal hit in performance while being capable of open set recognition for 3D point cloud data.

cs.CV↗

arXiv2020

Supervised Learning Using a Dressed Quantum Network with "Super Compressed Encoding": Algorithm and Quantum-Hardware-Based Implementation

Implementation of variational Quantum Machine Learning (QML) algorithms on Noisy Intermediate-Scale Quantum (NISQ) devices is known to have issues related to the high number of qubits needed and the noise associated with multi-qubit gates. In this paper, we propose a variational QML algorithm using a dressed quantum network to address these issues. Using the "super compressed encoding" scheme that we follow here, the classical encoding layer in our dressed network drastically scales down the input-dimension, before feeding the input to the variational quantum circuit. Hence, the number of qubits needed in our quantum circuit goes down drastically. Also, unlike in most other existing QML algorithms, our quantum circuit consists only of single-qubit gates, making it robust against noise. These factors make our algorithm suitable for implementation on NISQ hardware. To support our argument, we implement our algorithm on real NISQ hardware and thereby show accurate classification using popular machine learning data-sets like Fisher's Iris, Wisconsin's Breast Cancer (WBC), and Abalone. Then, to provide an intuitive explanation for our algorithm's working, we demonstrate the clustering of quantum states, which correspond to the input-samples of different output-classes, on the Bloch sphere (using WBC and MNIST data-sets). This clustering happens as a result of the training process followed in our algorithm. Through this Bloch-sphere-based representation, we also show the distinct roles played (in training) by the adjustable parameters of the classical encoding layer and the adjustable parameters of the variational quantum circuit. These parameters are adjusted iteratively during training through loss-minimization.

quant-ph↗

arXiv2020

Distilling Spikes: Knowledge Distillation in Spiking Neural Networks

Spiking Neural Networks (SNN) are energy-efficient computing architectures that exchange spikes for processing information, unlike classical Artificial Neural Networks (ANN). Due to this, SNNs are better suited for real-life deployments. However, similar to ANNs, SNNs also benefit from deeper architectures to obtain improved performance. Furthermore, like the deep ANNs, the memory, compute and power requirements of SNNs also increase with model size, and model compression becomes a necessity. Knowledge distillation is a model compression technique that enables transferring the learning of a large machine learning model to a smaller model with minimal loss in performance. In this paper, we propose techniques for knowledge distillation in spiking neural networks for the task of image classification. We present ways to distill spikes from a larger SNN, also called the teacher network, to a smaller one, also called the student network, while minimally impacting the classification accuracy. We demonstrate the effectiveness of the proposed method with detailed experiments on three standard datasets while proposing novel distillation methodologies and loss functions. We also present a multi-stage knowledge distillation technique for SNNs using an intermediate network to obtain higher performance from the student network. Our approach is expected to open up new avenues for deploying high performing large SNN models on resource-constrained hardware platforms.

cs.NE↗

arXiv2019

Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification

We deal with the problem of information fusion driven satellite image/scene classification and propose a generic hallucination architecture considering that all the available sensor information are present during training while some of the image modalities may be absent while testing. It is well-known that different sensors are capable of capturing complementary information for a given geographical area and a classification module incorporating information from all the sources are expected to produce an improved performance as compared to considering only a subset of the modalities. However, the classical classifier systems inherently require all the features used to train the module to be present for the test instances as well, which may not always be possible for typical remote sensing applications (say, disaster management). As a remedy, we provide a robust solution in terms of a hallucination module that can approximate the missing modalities from the available ones during the decision-making stage. In order to ensure better knowledge transfer during modality hallucination, we explicitly incorporate concepts of knowledge distillation for the purpose of exploring the privileged (side) information in our framework and subsequently introduce an intuitive modular training approach. The proposed network is evaluated extensively on a large-scale corpus of PAN-MS image pairs (scene recognition) as well as on a benchmark hyperspectral image dataset (image classification) where we follow different experimental scenarios and find that the proposed hallucination based module indeed is capable of capturing the multi-source information, albeit the explicit absence of some of the sensor information, and aid in improved scene characterization.

cs.CV↗

arXiv2019

CMB Spectral Distortions from Cooling Macroscopic Dark Matter

We propose a new mechanism by which dark matter (DM) can affect the early universe. The hot interior of a macroscopic DM, or macro, can behave as a heat reservoir so that energetic photons are emitted from its surface. This results in spectral distortions (SDs) of the cosmic microwave background. The SDs depend on the density and the cooling processes of the interior, and the surface composition of the Macros. We use neutron stars as a model for nuclear-density Macros and find that the spectral distortions are mass-independent for fixed density. In our work, we find that, for Macros of this type that constitute 100$\%$ of the dark matter, the $μ$ and $y$ distortions can be above detection threshold for typical proposed next-generation experiments such as PIXIE.

astro-ph.CO↗

arXiv2019

DeepMDP: Learning Continuous Latent Space Models for Representation Learning

Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a DeepMDP, a parameterized latent space model that is trained via the minimization of two tractable losses: prediction of rewards and prediction of the distribution over next latent states. We show that the optimization of these objectives guarantees (1) the quality of the latent space as a representation of the state space and (2) the quality of the DeepMDP as a model of the environment. We connect these results to prior work in the bisimulation literature, and explore the use of a variety of metrics. Our theoretical findings are substantiated by the experimental result that a trained DeepMDP recovers the latent structure underlying high-dimensional observations on a synthetic environment. Finally, we show that learning a DeepMDP as an auxiliary task in the Atari 2600 domain leads to large performance improvements over model-free RL.

cs.LG↗

arXiv2019

Statistics and Samples in Distributional Reinforcement Learning

We present a unifying framework for designing and analysing distributional reinforcement learning (DRL) algorithms in terms of recursively estimating statistics of the return distribution. Our key insight is that DRL algorithms can be decomposed as the combination of some statistical estimator and a method for imputing a return distribution consistent with that set of statistics. With this new understanding, we are able to provide improved analyses of existing DRL algorithms as well as construct a new algorithm (EDRL) based upon estimation of the expectiles of the return distribution. We compare EDRL with existing methods on a variety of MDPs to illustrate concrete aspects of our analysis, and develop a deep RL variant of the algorithm, ER-DQN, which we evaluate on the Atari-57 suite of games.

stat.ML↗

arXiv2018

Dopamine: A Research Framework for Deep Reinforcement Learning

Deep reinforcement learning (deep RL) research has grown significantly in recent years. A number of software offerings now exist that provide stable, comprehensive implementations for benchmarking. At the same time, recent deep RL research has become more diverse in its goals. In this paper we introduce Dopamine, a new research framework for deep RL that aims to support some of that diversity. Dopamine is open-source, TensorFlow-based, and provides compact and reliable implementations of some state-of-the-art deep RL agents. We complement this offering with a taxonomy of the different research objectives in deep RL research. While by no means exhaustive, our analysis highlights the heterogeneity of research in the field, and the value of frameworks such as ours.

cs.LG↗