Author name cluster

Gautam Shroff

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

AAAI Conference 2025 Conference Paper

ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)

Kartik Singhal
Gautam Shroff

The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods, including large language models (LLMs). While LLMs excel in program synthesis, their direct application to ARC yields limited success. To address this, we introduce ConceptSearch, a novel function-search algorithm that leverages LLMs for program generation and employs a concept-based scoring method to guide the search efficiently. Unlike simplistic pixel-based metrics like Hamming distance, ConceptSearch evaluates programs on their ability to capture the underlying transformation concept reflected in the input-output examples. We explore three scoring functions: Hamming distance, a CNN-based scoring function, and an LLM-based natural language scoring function. Experimental results demonstrate the effectiveness of ConceptSearch, achieving a significant performance improvement over direct prompting with GPT-4. Moreover, our novel concept-based scoring exhibits up to 30\% greater efficiency compared to Hamming distance, measured in terms of the number of iterations required to reach the correct solution. These findings highlight the potential of LLM-driven program search when integrated with concept-based guidance for tackling challenging generalization problems like ARC.

PDF Details DOI

AAAI Conference 2025 Short Paper

ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC) (Student Abstract)

Kartik Singhal
Gautam Shroff

PDF Details DOI

NeSy Conference 2022 Conference Paper

Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces

Vishwa Shah
Aditya Sharma
Gautam Shroff
Lovekesh Vig
Tirtharaj Dash
Ashwin Srinivasan 0001

Analogical Reasoning problems pose unique challenges for both connectionist and symbolic AI systems as these entail a carefully crafted solution combining background knowledge, deductive reasoning and visual pattern recognition. While symbolic systems are designed to ingest explicit domain knowledge and perform deductive reasoning, they are sensitive to noise and require inputs be mapped to a predetermined set of symbolic features. Connectionist systems on the other hand are able to directly ingest rich input spaces such as images, text or speech and can perform robust pattern recognition even with noisy inputs. However connectionist models struggle to incorporate explicit domain knowledge and perform deductive reasoning. In this paper, we propose a framework that combines the pattern recognition capabilities of neural networks with symbolic reasoning and background knowledge for solving a class of Analogical Reasoning problems where the set of example attributes and possible relations across them are known apriori. We take inspiration from the ‘neural algorithmic reasoning’ approach [DeepMind 2020] and exploit problem-specific background knowledge by (i) learning a distributed representation based on a symbolic model of the current problem (ii) training neural-network transformations reflective of the relations involved in the problem and finally (iii) training a neural network encoder from images to the distributed representation in (i). These three elements enable us to perform search-based reasoning using neural networks as elementary functions manipulating distributed representations. We test our approach on visual analogy problems in RAVENs Progressive Matrices, and achieve accuracy competitive with human performance and, in certain cases, superior to initial end-to-end neural-network based approaches. While recent neural models trained at scale currently yield the overall SOTA, we submit that our novel neuro-symbolic reasoning approach is a promising direction for this problem, and is arguably more general, especially for problems where sufficient domain knowledge is available.

Details

NeSy Conference 2022 Conference Paper

Neural Analogical Reasoning

Atharv Sonwane
Abhinav Lalwani
Sweta Mahajan
Gautam Shroff
Lovekesh Vig

Symbolic systems excel at reusing and composing modular functional units when solving problems such as simple analogical reasoning. However, they are less amenable to processing real-world data (e. g. images), and rely on additional (often hard-coded) mechanisms to convert such high-dimensional data to symbolic descriptions. In this work, we describe a modular approach ‘Neural Analogical Reasoning’ wherein elementary neural transformations operate and compose on distributed representations of high-dimensional inputs. We apply this approach on a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input-output images are related, so as to analogously transform future inputs. This can be viewed as a program synthesis task and solved via symbolic search if represented in symbolic form. Instead, we search for a sequence of elementary neural network transformations that manipulate distributed representations of the inputs. We present two variations of learning useful representations for this task and compare both with end-to-end meta-learning based approaches to demonstrate the importance of performing an explicit search.

Details

AAAI Conference 2022 Short Paper

Solving Visual Analogies Using Neural Algorithmic Reasoning (Student Abstract)

Atharv Sonwane
Gautam Shroff
Lovekesh Vig
Ashwin Srinivasan
Tirtharaj Dash

We consider a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input/output images are related, so as to analogously transform future inputs. This program synthesis task can be easily solved via symbolic search. Using a variation of the ‘neural analogical reasoning’ approach, we instead search for a sequence of elementary neural network transformations that manipulate distributed representations derived from a symbolic space, to which input images are directly encoded. We evaluate the extent to which our ‘neural reasoning’ approach generalises for images with unseen shapes and positions.

PDF Details

AAMAS Conference 2019 Conference Paper

A Reinforcement Learning Framework for Container Selection and Ship Load Sequencing in Ports

Richa Verma
Sarmimala Saikia
Harshad Khadilkar
Puneet Agarwal
Gautam Shroff
Ashwin Srinivasan

We describe a reinforcement learning (RL) framework for selecting and sequencing containers to load onto ships in ports. The goal is to minimize an approximation of the number of crane movements require to load a given ship, known as the shuffle count. It can be viewed as a version of the assignment problem in which the sequence of assignment is of importance and the task rewards are order dependent. The proposed methodology is developed specifically to be usable on ship and yard layouts of arbitrary scale, by dividing the full problem into fixed future horizon segments and through a redefinition of the action space into a binary choice framework. Using data from real-world yard and ship layouts, we show that our approach solves the single crane version of the loading problem for entire ships with better objective values than those computed using standard metaheuristics.

PDF

NeSy Conference 2019 Conference Paper

One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis

Vishal Sunder
Ashwin Srinivasan 0001
Lovekesh Vig
Gautam Shroff
Rohit Rahul

Our interest in this paper is in meeting a rapidly growing industrial demand for information extraction from images of documents such as invoices, bills, receipts etc. In practice users are able to provide a very small number of example images labeled with the information that needs to be extracted. We adopt a novel ‘two-level’‘neurodeductive’, approach where (a) we use pre-trained deep neural networks to populate a relational database with facts about each document-image; and (b) we use a form of deductive reasoning, related to meta-interpretive learning of transition systems to learn extraction programs: Given task-specific transitions defined using the entities and relations identified by the neural detectors and a small number of instances (usually 1, sometimes 2) of images and the desired outputs, a resource-bounded meta-interpreter constructs proofs for the instance(s) via logical deduction; a set of logic programs that extract each desired entity is easily synthesized from such proofs. In most cases a single training example together with a noisy-clone of itself suffices to learn a program-set that generalizes well on test documents, at which time the value of each entity is determined by a majority vote across its program-set. We demonstrate our two-level neuro-deductive approach on publicly available datasets (“Patent” and “Doctor’s Bills”) and also describe its use in a real-life industrial problem.

Details

AAAI Conference 2019 Short Paper

Regularizing Fully Convolutional Networks for Time Series Classification by Decorrelating Filters

Kaushal Paneri
Vishnu TV
Pankaj Malhotra
Lovekesh Vig
Gautam Shroff

Deep neural networks are prone to overfitting, especially in small training data regimes. Often, these networks are overparameterized and the resulting learned weights tend to have strong correlations. However, convolutional networks in general, and fully convolution neural networks (FCNs) in particular, have been shown to be relatively parameter efficient, and have recently been successfully applied to time series classification tasks. In this paper, we investigate the application of different regularizers on the correlation between the learned convolutional filters in FCNs using Batch Normalization (BN) as a regularizer for time series classification (TSC) tasks. Results demonstrate that despite orthogonal initialization of the filters, the average correlation across filters (especially for filters in higher layers) tends to increase as training proceeds, indicating redundancy of filters. To mitigate this redundancy, we propose a strong regularizer, using simple yet effective filter decorrelation. Our proposed method yields significant gains in classification accuracy for 44 diverse time series datasets from the UCR TSC benchmark repository.

PDF Details

EUMAS Conference 2015 Conference Paper

Group-Based Pricing to Shape Demand in Real-Time Electricity Markets

Rahul Agrawal
Anirban Chakraborti
Karamjit Singh
Gautam Shroff
Venkatesh Sarangan

Abstract Maintaining the balance between electricity supply and demand is one of the major concerns of utility operators. With the increasing contribution of renewable energy sources in the typical supply portfolio of an energy provider, volatility in supply is increasing while the control is decreasing. Real time pricing based on aggregate demand, unfortunately cannot control the non-linear price sensitivity of deferrable/flexible loads and leads to other peaks [ 4, 5 ] due to overly homogenous consumption response. In this paper, we present a day-ahead group-based real-time pricing mechanism for optimal demand shaping. We use agent-based simulations to model the system-wide consequences of deploying different pricing mechanisms and design a heuristic search mechanism in the strategy space to efficiently arrive at an optimal strategy. We prescribe a pricing mechanism for each groups of consumers, such that even though consumption synchrony within each group gives rise to local peaks, these happen at different time slots, which when aggregated result in a flattened macro demand response. Simulation results show that our group-based pricing strategy out-performs traditional real-time pricing, and results in a fairly flat peak-to-average ratio.

Details DOI