arXiv subjects

Karan Singh

Publications and source records attributed to Karan Singh.

At least 37 records · Page 2Linked to original sources

arXiv2025

Sample-Optimal Agnostic Boosting with Unlabeled Data

Boosting provides a practical and provably effective framework for constructing accurate learning algorithms from inaccurate rules of thumb. It extends the promise of sample-efficient learning to settings where direct Empirical Risk Minimization (ERM) may not be implementable efficiently. In the realizable setting, boosting is known to offer this computational reprieve without compromising on sample efficiency. However, in the agnostic case, existing boosting algorithms fall short of achieving the optimal sample complexity. This paper highlights an unexpected and previously unexplored avenue of improvement: unlabeled samples. We design a computationally efficient agnostic boosting algorithm that matches the sample complexity of ERM, given polynomially many additional unlabeled samples. In fact, we show that the total number of samples needed, unlabeled and labeled inclusive, is never more than that for the best known agnostic boosting algorithm -- so this result is never worse -- while only a vanishing fraction of these need to be labeled for the algorithm to succeed. This is particularly fortuitous for learning-theoretic applications of agnostic boosting, which often take place in the distribution-specific setting, where unlabeled samples can be availed for free. We detail other applications of this result in reinforcement learning.

cs.LG↗

arXiv2025

Faster Global Minimum Cut with Predictions

Global minimum cut is a fundamental combinatorial optimization problem with wide-ranging applications. Often in practice, these problems are solved repeatedly on families of similar or related instances. However, the de facto algorithmic approach is to solve each instance of the problem from scratch discarding information from prior instances. In this paper, we consider how predictions informed by prior instances can be used to warm-start practical minimum cut algorithms. The paper considers the widely used Karger's algorithm and its counterpart, the Karger-Stein algorithm. Given good predictions, we show these algorithms become near-linear time and have robust performance to erroneous predictions. Both of these algorithms are randomized edge-contraction algorithms. Our natural idea is to probabilistically prioritize the contraction of edges that are unlikely to be in the minimum cut.

cs.DS↗

arXiv2024

Motion Modes: What Could Happen Next?

Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific motions from motion arrow input, they rely on synthetic data and predefined motions, limiting their application to complex scenes. We introduce Motion Modes, a training-free approach that explores a pre-trained image-to-video generator's latent distribution to discover various distinct and plausible motions focused on selected objects in static images. We achieve this by employing a flow generator guided by energy functions designed to disentangle object and camera motion. Additionally, we use an energy inspired by particle guidance to diversify the generated motions, without requiring explicit training data. Experimental results demonstrate that Motion Modes generates realistic and varied object animations, surpassing previous methods and even human predictions regarding plausibility and diversity. Project Webpage: https://motionmodes.github.io/

cs.CV↗

arXiv2024

Sample-Efficient Agnostic Boosting

The theory of boosting provides a computational framework for aggregating approximate weak learning algorithms, which perform marginally better than a random predictor, into an accurate strong learner. In the realizable case, the success of the boosting approach is underscored by a remarkable fact that the resultant sample complexity matches that of a computationally demanding alternative, namely Empirical Risk Minimization (ERM). This in particular implies that the realizable boosting methodology has the potential to offer computational relief without compromising on sample efficiency. Despite recent progress, in agnostic boosting, where assumptions on the conditional distribution of labels given feature descriptions are absent, ERM outstrips the agnostic boosting methodology in being quadratically more sample efficient than all known agnostic boosting algorithms. In this paper, we make progress on closing this gap, and give a substantially more sample efficient agnostic boosting algorithm than those known, without compromising on the computational (or oracle) complexity. A key feature of our algorithm is that it leverages the ability to reuse samples across multiple rounds of boosting, while guaranteeing a generalization error strictly better than those obtained by blackbox applications of uniform convergence arguments. We also apply our approach to other previously studied learning problems, including boosting for reinforcement learning, and demonstrate improved results.

cs.LG↗

arXiv2024

Evidence of variable range hopping in the Zintl phase EuIn2P2

We report a comprehensive characterization of the magnetic, electrical transport, spectral, and thermal properties of single-crystalline Zintl-type material EuIn2P2. The compound crystallizes with a hexagonal unit cell (space group P63/mmc) and orders magnetically at TC=24K with the Eu magnetic moments aligned ferromagnetically within the ab plane but tilted alternately along the c-axis direction. The effective and saturation magnetic moments agree with the theoretical values expected for the Eu2+ ion. For a range of several tens of kelvins above 40K, the electrical transport of EuIn2P2 is dominated by short-range magnetic interactions. The temperature dependence of the electrical resistivity has been modelled in terms of variable-range hopping. Another indication of the latter scenario seems to be the observation for EuIn2P2 of a quadratic dependence of the negative magnetoresistance on the magnetic field strength and the scaled magnetization. The temperature dependence of Raman band position and FWHM, as well as phonon lifetime, confirms the presence of the distinctive regions observed in transport and magnetic studies.

cond-mat.mtrl-sci↗

arXiv2024

Streamlined approach to mitigation of cascading failure in complex networks

Cascading failures represent a fundamental threat to the integrity of complex systems, often precipitating a comprehensive collapse across diverse infrastructures and financial networks. This research articulates a robust and pragmatic approach designed to attenuate the risk of such failures within complex networks, emphasizing the pivotal role of local network topology. The core of our strategy is an innovative algorithm that systematically identifies a subset of critical nodes within the network, a subset whose relative size is substantial in the context of the network's entirety. Enhancing this algorithm, we employ a graph coloring heuristic to precisely isolate nodes of paramount importance, thereby minimizing the subset size while maximizing strategic value. Securing these nodes significantly bolsters network resilience against cascading failures. The method proposed to identify critical nodes and experimental results show that the proposed technique outperforms other typical techniques in identifying critical nodes. We substantiate the superiority of our approach through comparative analyses with existing mitigation strategies and evaluate its performance across various network configurations and failure scenarios. Empirical validation is provided via the application of our method to real-world networks, confirming its potential as a strategic tool in enhancing network robustness.

nlin.AO↗

arXiv2024

Large unconventional anomalous Hall effect arising from spin chirality within domain walls of an antiferromagnet EuZn$_2$Sb$_2$

Unconventional anomalous Hall effect was observed in antiferromagnetic state of EuZn$_2$Sb$_2$. Scaling of unconventional Hall conductivity with the longitudinal conductivity, and the magnitude of Hall angle indicate spin chirality despite collinear magnetic structure. Anomalies in magnetoresistance culminate in the same fields, in which the unconventional anomalous Hall resistance has maxima. Monotonous decrease of their magnitude with increasing temperature belittles here the role of spin-fluctuations, important in isostructural compounds. These observations point to a prominent role of scalar spin chirality within domain walls, when magnetic field tilts the Eu moments. Simple calculation of such spin chirality shows it strongest in fields characteristic for anomalous magnetotransport.

cond-mat.mtrl-sci↗

arXiv2023

Improved Differentially Private and Lazy Online Convex Optimization

We study the task of $(ε, δ)$-differentially private online convex optimization (OCO). In the online setting, the release of each distinct decision or iterate carries with it the potential for privacy loss. This problem has a long history of research starting with Jain et al. [2012] and the best known results for the regime of ε not being very small are presented in Agarwal et al. [2023]. In this paper we improve upon the results of Agarwal et al. [2023] in terms of the dimension factors as well as removing the requirement of smoothness. Our results are now the best known rates for DP-OCO in this regime. Our algorithms builds upon the work of [Asi et al., 2023] which introduced the idea of explicitly limiting the number of switches via rejection sampling. The main innovation in our algorithm is the use of sampling from a strongly log-concave density which allows us to trade-off the dimension factors better leading to improved results.

cs.CR↗

arXiv2023

Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D

Diffusion Handles is a novel approach to enabling 3D object edits on diffusion images. We accomplish these edits using existing pre-trained diffusion models, and 2D image depth estimation, without any fine-tuning or 3D object retrieval. The edited results remain plausible, photo-real, and preserve object identity. Diffusion Handles address a critically missing facet of generative image based creative design, and significantly advance the state-of-the-art in generative image editing. Our key insight is to lift diffusion activations for an object to 3D using a proxy depth, 3D-transform the depth and associated activations, and project them back to image space. The diffusion process applied to the manipulated activations with identity control, produces plausible edited images showing complex 3D occlusion and lighting effects. We evaluate Diffusion Handles: quantitatively, on a large synthetic data benchmark; and qualitatively by a user study, showing our output to be more plausible, and better than prior art at both, 3D editing and identity control. Project Webpage: https://diffusionhandles.github.io/

cs.CV↗

arXiv2023

Malware Analysis on AI Technique

In today's world, we are performing our maximum work through the Internet, i.e., online payment, data transfer, etc., per day. More than thousands of users are connecting. So, it's essential to provide security to the user. It is necessary to detect and prevent malicious object from gaining persistence and causing destruction within the organization. Therefore, Malware analysis is needed in order to secure the system. This necessitates the use of effective and efficient approaches for detecting OS malware. Due to the cheap cost of technology, artificial intelligence has also become less difficult to implement in projects to analyse malware. The categorization and analysis of malware on OS using various AI-based analysis techniques are covered in detail in this paper.

cs.CR↗

arXiv2023

Online Nonstochastic Model-Free Reinforcement Learning

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of unmodeled disturbances in such settings. Moreover, optimizing linear state-based policies pose an obstacle for efficient optimization, leading to nonconvex objectives, even in benign environments like linear dynamical systems. Drawing inspiration from recent advancements in model-based control, we introduce a novel class of policies centered on disturbance signals. We define several categories of these signals, which we term pseudo-disturbances, and develop corresponding policy classes based on them. We provide efficient and practical algorithms for optimizing these policies. Next, we examine the task of online adaptation of reinforcement learning agents in the face of adversarial disturbances. Our methods seamlessly integrate with any black-box model-free approach, yielding provable regret guarantees when dealing with linear dynamics. These regret guarantees unconditionally improve the best-known results for bandit linear control in having no dependence on the state-space dimension. We evaluate our method over various standard RL benchmarks and demonstrate improved robustness.

cs.LG↗

arXiv2023

Superexchange Interaction in Insulating EuZn$_{2}$P$_{2}$

We report magnetic and transport properties of single-crystalline EuZn$_{2}$P$_{2}$, which has trigonal CaAl$_2$Si$_2$-type crystal structure and orders antiferromagnetically at $\approx$23~K. Easy $ab$-plane magneto-crystalline anisotropy was confirmed from the magnetization isotherms, measured with a magnetic field applied along different crystallographic directions ($ab$-plane and $c$-axis). Positive Curie-Weiss temperature indicates dominating ferromagnetic correlations. Electrical resistivity displays insulating behavior with a band-gap of $\approx\,$0.177~eV, which decreases to $\approx\,$0.13~eV upon application of a high magnetic field. We explained the intriguing presence of magnetic interactions in an intermetallic insulator by the mechanism of extended superexchange, with phosphorus as an anion mediator, which is further supported by our analysis of the charge and spin density distributions. We constructed the effective Heisenberg model, with exchange parameters derived from the \textit{ab initio} DFT calculations, and employed it in Monte-Carlo simulations, which correctly reproduced the experimental value of Néel temperature.

cond-mat.mtrl-sci↗

arXiv2023

MAGIC: Manipulating Avatars and Gestures to Improve Remote Collaboration

Remote collaborative work has become pervasive in many settings, from engineering to medical professions. Users are immersed in virtual environments and communicate through life-sized avatars that enable face-to-face collaboration. Within this context, users often collaboratively view and interact with virtual 3D models, for example, to assist in designing new devices such as customized prosthetics, vehicles, or buildings. However, discussing shared 3D content face-to-face has various challenges, such as ambiguities, occlusions, and different viewpoints that all decrease mutual awareness, leading to decreased task performance and increased errors. To address this challenge, we introduce MAGIC, a novel approach for understanding pointing gestures in a face-to-face shared 3D space, improving mutual understanding and awareness. Our approach distorts the remote userś gestures to correctly reflect them in the local userś reference space when face-to-face. We introduce a novel metric called pointing agreement to measure what two users perceive in common when using pointing gestures in a shared 3D space. Results from a user study suggest that MAGIC significantly improves pointing agreement in face-to-face collaboration settings, improving co-presence and awareness of interactions performed in the shared space. We believe that MAGIC improves remote collaboration by enabling simpler communication mechanisms and better mutual awareness.

cs.HC↗

arXiv2023

A Boosting Approach to Reinforcement Learning

Reducing reinforcement learning to supervised learning is a well-studied and effective approach that leverages the benefits of compact function approximation to deal with large-scale Markov decision processes. Independently, the boosting methodology (e.g. AdaBoost) has proven to be indispensable in designing efficient and accurate classification algorithms by combining inaccurate rules-of-thumb. In this paper, we take a further step: we reduce reinforcement learning to a sequence of weak learning problems. Since weak learners perform only marginally better than random guesses, such subroutines constitute a weaker assumption than the availability of an accurate supervised learning oracle. We prove that the sample complexity and running time bounds of the proposed method do not explicitly depend on the number of states. While existing results on boosting operate on convex losses, the value function over policies is non-convex. We show how to use a non-convex variant of the Frank-Wolfe method for boosting, that additionally improves upon the known sample complexity and running time even for reductions to supervised learning.

cs.LG↗

arXiv2023

Variance-Reduced Conservative Policy Iteration

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to the parameter space for policy gradient algorithms, and thus are unaffected by the possibly non-linear or discontinuous parameterization of the policy class. We propose a variance-reduced variant of Conservative Policy Iteration that improves the sample complexity of producing a $\varepsilon$-functional local optimum from $O(\varepsilon^{-4})$ to $O(\varepsilon^{-3})$. Under state-coverage and policy-completeness assumptions, the algorithm enjoys $\varepsilon$-global optimality after sampling $O(\varepsilon^{-2})$ times, improving upon the previously established $O(\varepsilon^{-3})$ sample requirement.

cs.LG↗

arXiv2022

Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret

We consider the fundamental problem of online control of a linear dynamical system from two different viewpoints: regret minimization and competitive analysis. We prove that the optimal competitive policy is well-approximated by a convex parameterized policy class, known as a disturbance-action control (DAC) policies. Using this structural result, we show that several recently proposed online control algorithms achieve the best of both worlds: sublinear regret vs. the best DAC policy selected in hindsight, and optimal competitive ratio, up to an additive correction which grows sublinearly in the time horizon. We further conclude that sublinear regret vs. the optimal competitive policy is attainable when the linear dynamical system is unknown, and even when a stabilizing controller for the dynamics is not available a priori.

cs.LG↗

arXiv2022

Melting of spin ice state and development of fifth order susceptibility with magnetic field in pyrochlore Tb2Sn2O7

Pyrochlores offer an ideal playground to investigate the magnetic ground state of frustrated magnetic systems. In this class of materials, competition between various magnetic interactions remains frustrated and prevents an ordered magnetic state at low temperatures. Tb2Sn2O7 has recently attracted significant attention due to its ordered spin-ice state. Additionally, in such systems, application of external magnetic field might result in exotic magnetic states. Our current investigation on Tb2Sn2O7 reveal the presence of a new phase associated with fifth order susceptibility at low temperatures and high magnetic fields. In this compound, at zero fields, for a stabilized spin-ice state, the singlet-singlet state separated by δ play an imperative role. Under magnetic fields, δ increases and the Zeeman energy associated with the magnetic anisotropy is believed to get enhanced; which can be the key ingredient for evolution of higher-order moments, above 10 kOe, in this compound.

cond-mat.str-el↗

arXiv2022

Machine Learning for Mechanical Ventilation Control

We consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patient's lungs according to a trajectory of airway pressures specified by a clinician. Hand-tuned PID controllers and similar variants have comprised the industry standard for decades, yet can behave poorly by over- or under-shooting their target or oscillating rapidly. We consider a data-driven machine learning approach: First, we train a simulator based on data we collect from an artificial lung. Then, we train deep neural network controllers on these simulators.We show that our controllers are able to track target pressure waveforms significantly better than PID controllers. We further show that a learned controller generalizes across lungs with varying characteristics much more readily than PID controllers do.

cs.LG↗