arXiv subjects

Avishek Ghosh

Publications and source records attributed to Avishek Ghosh.

47 records · Page 3Linked to original sources

arXiv2019

Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation

Max-affine regression refers to a model where the unknown regression function is modeled as a maximum of $k$ unknown affine functions for a fixed $k \geq 1$. This generalizes linear regression and (real) phase retrieval, and is closely related to convex regression. Working within a non-asymptotic framework, we study this problem in the high-dimensional setting assuming that $k$ is a fixed constant, and focus on estimation of the unknown coefficients of the affine functions underlying the model. We analyze a natural alternating minimization (AM) algorithm for the non-convex least squares objective when the design is random. We show that the AM algorithm, when initialized suitably, converges with high probability and at a geometric rate to a small ball around the optimal coefficients. In order to initialize the algorithm, we propose and analyze a combination of a spectral method and a random search scheme in a low-dimensional space, which may be of independent interest. The final rate that we obtain is near-parametric and minimax optimal (up to a poly-logarithmic factor) as a function of the dimension, sample size, and noise variance. In that sense, our approach should be viewed as a direct and implementable method of enforcing regularization to alleviate the curse of dimensionality in problems of the convex regression type. As a by-product of our analysis, we also obtain guarantees on a classical algorithm for the phase retrieval problem under considerably weaker assumptions on the design distribution than was previously known. Numerical experiments illustrate the sharpness of our bounds in the various problem parameters.

stat.ML↗

arXiv2018

Online Scoring with Delayed Information: A Convex Optimization Viewpoint

We consider a system where agents enter in an online fashion and are evaluated based on their attributes or context vectors. There can be practical situations where this context is partially observed, and the unobserved part comes after some delay. We assume that an agent, once left, cannot re-enter the system. Therefore, the job of the system is to provide an estimated score for the agent based on her instantaneous score and possibly some inference of the instantaneous score over the delayed score. In this paper, we estimate the delayed context via an online convex game between the agent and the system. We argue that the error in the score estimate accumulated over $T$ iterations is small if the regret of the online convex game is small. Further, we leverage side information about the delayed context in the form of a correlation function with the known context. We consider the settings where the delay is fixed or arbitrarily chosen by an adversary. Furthermore, we extend the formulation to the setting where the contexts are drawn from some Banach space. Overall, we show that the average penalty for not knowing the delayed context while making a decision scales with $\mathcal{O}(\frac{1}{\sqrt{T}})$, where this can be improved to $\mathcal{O}(\frac{\log T}{T})$ under special setting.

cs.LG↗

arXiv2018

Faster Data-access in Large-scale Systems: Network-scale Latency Analysis under General Service-time Distributions

In cloud storage systems with a large number of servers, files are typically not stored in single servers. Instead, they are split, replicated (to ensure reliability in case of server malfunction) and stored in different servers. We analyze the mean latency of such a split-and-replicate cloud storage system under general sub-exponential service time. We present a novel scheduling scheme that utilizes the load-balancing policy of the \textit{power of $d$ $(\geq 2)$} choices. An alternative to split-and-replicate is to use erasure-codes, and recently, it has been observed that they can reduce latency in data access (see \cite{longbo_delay} for details). We argue that under high redundancy (integer redundancy factor strictly greater than or equal to 2) regime, the mean latency of a coded system is upper bounded by that of a split-and-replicate system (with same replication factor) and the gap between these two is small. We validate this claim numerically under different service distributions such as exponential, shift plus exponential and the heavy-tailed Weibull distribution and compare the mean latency to that of an unsplit-replicated system. We observe that the coded system outperforms the unsplit-replication system by at least $20\%$. Furthermore, we consider the mean latency for an erasure coded system with low redundancy (fractional redundancy factor between 1 and 2), a scenario which is more pragmatic, given the storage constraints (\cite{rashmi_thesis}). However under this regime, we restrict ourselves to the special case of exponential service time distribution and use the randomized load balancing policy namely \textit{batch-sampling}. We obtain an upper bound on mean delay that depends on the order statistics of the queue lengths, which, we further smooth out via a discrete to continuous approximation.

cs.DC↗

arXiv2017

Asynchronous Stochastic Approximation Based Learning Algorithms for As-You-Go Deployment of Wireless Relay Networks along a Line

We are motivated by the need for impromptu (or as-you-go) deployment of multihop wireless networks, by human agents or robots; the agent moves along a line, makes wireless link quality measurements at regular intervals, and makes on-line placement decisions using these measurements. As a first step, we have formulated such deployment along a line as a sequential decision problem. In our earlier work, we proposed two possible deployment approaches: (i) the pure as-you-go approach where the deployment agent can only move forward, and (ii) the explore-forward approach where the deployment agent explores a few successive steps and then selects the best relay placement location. The latter was shown to provide better performance but at the expense of more measurements and deployment time, which makes explore-forward impractical for quick deployment by an energy constrained agent such as a UAV. Further, the deployment algorithm should not require prior knowledge of the parameters of the wireless propagation model. In [1] we, therefore, developed learning algorithms for the explore-forward approach. The current paper provides deploy-and-learn algorithms for the pure as-you-go approach. We formulate the sequential relay deployment problem as an average cost Markov decision process (MDP), which trades off among power consumption, link outage probabilities, and the number of deployed relay nodes. First we show structural results for the optimal policy. Next, by exploiting the special structure of the optimality equation and by using the theory of asynchronous stochastic approximation, we develop two learning algorithms that asymptotically converge to the set of optimal policies as deployment progresses. Numerical results show reasonably fast speed of convergence, and hence the model-free algorithms can be useful for practical, fast deployment of emergency wireless networks.

cs.NI↗

arXiv2017

Misspecified Linear Bandits

We consider the problem of online learning in misspecified linear stochastic multi-armed bandit problems. Regret guarantees for state-of-the-art linear bandit algorithms such as Optimism in the Face of Uncertainty Linear bandit (OFUL) hold under the assumption that the arms expected rewards are perfectly linear in their features. It is, however, of interest to investigate the impact of potential misspecification in linear bandit models, where the expected rewards are perturbed away from the linear subspace determined by the arms features. Although OFUL has recently been shown to be robust to relatively small deviations from linearity, we show that any linear bandit algorithm that enjoys optimal regret performance in the perfectly linear setting (e.g., OFUL) must suffer linear regret under a sparse additive perturbation of the linear model. In an attempt to overcome this negative result, we define a natural class of bandit models characterized by a non-sparse deviation from linearity. We argue that the OFUL algorithm can fail to achieve sublinear regret even under models that have non-sparse deviation.We finally develop a novel bandit algorithm, comprising a hypothesis test for linearity followed by a decision to use either the OFUL or Upper Confidence Bound (UCB) algorithm. For perfectly linear bandit models, the algorithm provably exhibits OFULs favorable regret performance, while for misspecified models satisfying the non-sparse deviation property, the algorithm avoids the linear regret phenomenon and falls back on UCBs sublinear regret scaling. Numerical experiments on synthetic data, and on recommendation data from the public Yahoo! Learning to Rank Challenge dataset, empirically support our findings.

cs.LG↗

arXiv2014

Impromptu Deployment of Wireless Relay Networks: Experiences Along a Forest Trail

We are motivated by the problem of impromptu or as- you-go deployment of wireless sensor networks. As an application example, a person, starting from a sink node, walks along a forest trail, makes link quality measurements (with the previously placed nodes) at equally spaced locations, and deploys relays at some of these locations, so as to connect a sensor placed at some a priori unknown point on the trail with the sink node. In this paper, we report our experimental experiences with some as-you-go deployment algorithms. Two algorithms are based on Markov decision process (MDP) formulations; these require a radio propagation model. We also study purely measurement based strategies: one heuristic that is motivated by our MDP formulations, one asymptotically optimal learning algorithm, and one inspired by a popular heuristic. We extract a statistical model of the propagation along a forest trail from raw measurement data, implement the algorithms experimentally in the forest, and compare them. The results provide useful insights regarding the choice of the deployment algorithm and its parameters, and also demonstrate the necessity of a proper theoretical formulation.

cs.NI↗

arXiv2012

An Evolutionary Approach to Drug-Design Using a Novel Neighbourhood Based Genetic Algorithm

The present work provides a new approach to evolve ligand structures which represent possible drug to be docked to the active site of the target protein. The structure is represented as a tree where each non-empty node represents a functional group. It is assumed that the active site configuration of the target protein is known with position of the essential residues. In this paper the interaction energy of the ligands with the protein target is minimized. Moreover, the size of the tree is difficult to obtain and it will be different for different active sites. To overcome the difficulty, a variable tree size configuration is used for designing ligands. The optimization is done using a novel Neighbourhood Based Genetic Algorithm (NBGA) which uses dynamic neighbourhood topology. To get variable tree size, a variable-length version of the above algorithm is devised. To judge the merit of the algorithm, it is initially applied on the well known Travelling Salesman Problem (TSP).

cs.NE↗

arXiv2012

Multi-robot Cooperative Box-pushing problem using Multi-objective Particle Swarm Optimization Technique

The present work provides a new approach to solve the well-known multi-robot co-operative box pushing problem as a multi objective optimization problem using modified Multi-objective Particle Swarm Optimization. The method proposed here allows both turning and translation of the box, during shift to a desired goal position. We have employed local planning scheme to determine the magnitude of the forces applied by the two mobile robots perpendicularly at specific locations on the box to align and translate it in each distinct step of motion of the box, for minimization of both time and energy. Finally the results are compared with the results obtained by solving the same problem using Non-dominated Sorting Genetic Algorithm-II (NSGA-II). The proposed scheme is found to give better results compared to NSGA-II.

cs.RO↗

arXiv2012

An Evolutionary Approach to Drug-Design Using Quantam Binary Particle Swarm Optimization Algorithm

The present work provides a new approach to evolve ligand structures which represent possible drug to be docked to the active site of the target protein. The structure is represented as a tree where each non-empty node represents a functional group. It is assumed that the active site configuration of the target protein is known with position of the essential residues. In this paper the interaction energy of the ligands with the protein target is minimized. Moreover, the size of the tree is difficult to obtain and it will be different for different active sites. To overcome the difficulty, a variable tree size configuration is used for designing ligands. The optimization is done using a quantum discrete PSO. The result using fixed length and variable length configuration are compared.

cs.NE↗

arXiv2012

Application of Integral Value Transformation (IVT) in a Specialized Computer Network Design

Integral Value Transformation (IVT) is a family of transformations from N0kto N0. An algebraic result has been established in p-adic IVT systems and an application of the result is described in this paper. The result in this paper provides the rule to find the pth pre image of a natural number for the Collatz like bijective functions in p-adic IVT systems. Using this result a routing algorithm is proposed. This proposed routing algorithm reduces number of address calculation.

cs.DM↗

arXiv2011

Fractal String Generation and Its Application in Music Composition

Music is a string of some of the notes out of 12 notes (Sa, Komal_re, Re, Komal_ga, Ga, Ma, Kari_ma, Pa, Komal_dha, Dha, Komal_ni, Ni) and their harmonics. Each note corresponds to a particular frequency. When such strings are encoded to form discrete sequences, different frequencies present in the music corresponds to different amplitude levels (value) of the discrete sequence. Initially, a class of discrete sequences has been generated using logistic map. All these discrete sequences have at most n-different amplitude levels (value) (depending on the particular raga). Without loss of generality, we have chosen two discrete sequences of two types of Indian raga viz. Bhairabi and Bhupali having same number of amplitude levels to obtain/search close relatives from the class. The relative / closeness can be assured through correlation coefficient.The search is unbiased, random and non-adaptive. The obtained string is that which maximally resembles the given two sequences. The same can be thought of as a music composition of the given two strings. It is to be noted that all these string are fractal string which can be persuaded by fractal dimension.

cs.SD↗