arXiv subjects

Shreyas Chaudhari

Publications and source records attributed to Shreyas Chaudhari.

27 records · Page 2Linked to original sources

arXiv2023

Distributional Off-Policy Evaluation for Slate Recommendations

Recommendation strategies are typically evaluated by using previously logged data, employing off-policy evaluation methods to estimate their expected performance. However, for strategies that present users with slates of multiple items, the resulting combinatorial action space renders many of these methods impractical. Prior work has developed estimators that leverage the structure in slates to estimate the expected off-policy performance, but the estimation of the entire performance distribution remains elusive. Estimating the complete distribution allows for a more comprehensive evaluation of recommendation strategies, particularly along the axes of risk and fairness that employ metrics computable from the distribution. In this paper, we propose an estimator for the complete off-policy performance distribution for slates and establish conditions under which the estimator is unbiased and consistent. This builds upon prior work on off-policy evaluation for slates and off-policy distribution estimation in reinforcement learning. We validate the efficacy of our method empirically on synthetic data as well as on a slate recommendation simulator constructed from real-world data (MovieLens-20M). Our results show a significant reduction in estimation variance and improved sample efficiency over prior work across a range of slate structures.

cs.IR↗

arXiv2023

From Past to Future: Rethinking Eligibility Traces

In this paper, we introduce a fresh perspective on the challenges of credit assignment and policy evaluation. First, we delve into the nuances of eligibility traces and explore instances where their updates may result in unexpected credit assignment to preceding states. From this investigation emerges the concept of a novel value function, which we refer to as the \emph{bidirectional value function}. Unlike traditional state value functions, bidirectional value functions account for both future expected returns (rewards anticipated from the current state onward) and past expected returns (cumulative rewards from the episode's start to the present). We derive principled update equations to learn this value function and, through experimentation, demonstrate its efficacy in enhancing the process of policy evaluation. In particular, our results indicate that the proposed learning approach can, in certain challenging contexts, perform policy evaluation more rapidly than TD($λ$) -- a method that learns forward value functions, $v^π$, \emph{directly}. Overall, our findings present a new perspective on eligibility traces and potential advantages associated with the novel value function it inspires, especially for policy evaluation.

cs.LG↗

arXiv2023

Learning Gradients of Convex Functions with Monotone Gradient Networks

While much effort has been devoted to deriving and analyzing effective convex formulations of signal processing problems, the gradients of convex functions also have critical applications ranging from gradient-based optimization to optimal transport. Recent works have explored data-driven methods for learning convex objective functions, but learning their monotone gradients is seldom studied. In this work, we propose C-MGN and M-MGN, two monotone gradient neural network architectures for directly learning the gradients of convex functions. We show that, compared to state of the art methods, our networks are easier to train, learn monotone gradient fields more accurately, and use significantly fewer parameters. We further demonstrate their ability to learn optimal transport mappings to augment driving image data.

cs.LG↗

arXiv2022

High-Resolution CMB Lensing Reconstruction with Deep Learning

Next-generation cosmic microwave background (CMB) surveys are expected to provide valuable information about the primordial universe by creating maps of the mass along the line of sight. Traditional tools for creating these lensing convergence maps include the quadratic estimator and the maximum likelihood based iterative estimator. Here, we apply a generative adversarial network (GAN) to reconstruct the lensing convergence field. We compare our results with a previous deep learning approach -- Residual-UNet -- and discuss the pros and cons of each. In the process, we use training sets generated by a variety of power spectra, rather than the one used in testing the methods.

astro-ph.CO↗

arXiv2021

Multi-Armed Bandits with Correlated Arms

We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. We develop a unified approach to leverage these reward correlations and present fundamental generalizations of classic bandit algorithms to the correlated setting. We present a unified proof technique to analyze the proposed algorithms. Rigorous analysis of C-UCB (the correlated bandit version of Upper-confidence-bound) reveals that the algorithm ends up pulling certain sub-optimal arms, termed as non-competitive, only O(1) times, as opposed to the O(log T) pulls required by classic bandit algorithms such as UCB, TS etc. We present regret-lower bound and show that when arms are correlated through a latent random source, our algorithms obtain order-optimal regret. We validate the proposed algorithms via experiments on the MovieLens and Goodreads datasets, and show significant improvement over classical bandit algorithms.

stat.ML↗

arXiv2021

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we formally show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the modified reward function penalizes the agent for visiting states and taking actions in the source domain which are not possible in the target domain. Said another way, the agent is penalized for transitions that would indicate that the agent is interacting with the source domain, rather than the target domain. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics. On discrete and continuous control tasks, we illustrate the mechanics of our approach and demonstrate its scalability to high-dimensional tasks.

cs.LG↗

arXiv2021

Unsupervised Clustering of Time Series Signals using Neuromorphic Energy-Efficient Temporal Neural Networks

Unsupervised time series clustering is a challenging problem with diverse industrial applications such as anomaly detection, bio-wearables, etc. These applications typically involve small, low-power devices on the edge that collect and process real-time sensory signals. State-of-the-art time-series clustering methods perform some form of loss minimization that is extremely computationally intensive from the perspective of edge devices. In this work, we propose a neuromorphic approach to unsupervised time series clustering based on Temporal Neural Networks that is capable of ultra low-power, continuous online learning. We demonstrate its clustering performance on a subset of UCR Time Series Archive datasets. Our results show that the proposed approach either outperforms or performs similarly to most of the existing algorithms while being far more amenable for efficient hardware implementation. Our hardware assessment analysis shows that in 7 nm CMOS the proposed architecture, on average, consumes only about 0.005 mm^2 die area and 22 uW power and can process each signal with about 5 ns latency.

cs.LG↗

arXiv2021

A Unified Approach to Translate Classical Bandit Algorithms to the Structured Bandit Setting

We consider a finite-armed structured bandit problem in which mean rewards of different arms are known functions of a common hidden parameter $θ^*$. Since we do not place any restrictions of these functions, the problem setting subsumes several previously studied frameworks that assume linear or invertible reward functions. We propose a novel approach to gradually estimate the hidden $θ^*$ and use the estimate together with the mean reward functions to substantially reduce exploration of sub-optimal arms. This approach enables us to fundamentally generalize any classic bandit algorithm including UCB and Thompson Sampling to the structured bandit setting. We prove via regret analysis that our proposed UCB-C algorithm (structured bandit versions of UCB) pulls only a subset of the sub-optimal arms $O(\log T)$ times while the other sub-optimal arms (referred to as non-competitive arms) are pulled $O(1)$ times. As a result, in cases where all sub-optimal arms are non-competitive, which can happen in many practical scenarios, the proposed algorithms achieve bounded regret. We also conduct simulations on the Movielens recommendations dataset to demonstrate the improvement of the proposed algorithms over existing structured bandit algorithms.

stat.ML↗

arXiv2017

Energy-Delay-Distortion Problem

An energy-limited source trying to transmit multiple packets to a destination with possibly different sizes is considered. With limited energy, the source cannot potentially transmit all bits of all packets. In addition, there is a delay cost associated with each packet. Thus, the source has to choose, how many bits to transmit for each packet, and the order in which to transmit these bits, to minimize the cost of distortion (introduced by transmitting lower number of bits) and queueing plus transmission delay, across all packets. Assuming an exponential metric for distortion loss and linear delay cost, we show that the optimization problem is jointly convex. Hence, the problem can be exactly solved using convex solvers, however, because of the complicated expression derived from the KKT conditions, no closed form solution can be found even with the simplest cost function choice made in the paper, also the optimal order in which packets should be transmitted needs to be found via brute force. To facilitate a more structured solution, a discretized version of the problem is also considered, where time and energy are divided in discrete amounts. In any time slot (fixed length), bits belonging to any one packet can be transmitted, while any discrete number of energy quanta can be used in any slot corresponding to any one packet, such that the total energy constraint is satisfied. The discretized problem is a special case of a multi-partitioning problem, where each packet's utility is super-modular and the proposed greedy solution is shown to incur cost that is at most $2$-times of the optimal cost.

cs.IT↗