Search Results for author:
Found 93 papers, 28 papers with code
International AI Safety Report
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems.
Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness
In this work, we study the effects on both task performance and fairness when the DLM algorithm, a recent work on using LLMs to design reward functions for RMABs, is prompted with non-English language commands.
QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities
We propose optimizations that enhance the efficiency of QuAKE in commonly used exponential non-linearities such as Softmax, GELU, and the Logistic function.
Deception in Reinforced Autonomous Agents
We explore the ability of large language model (LLM)-based agents to engage in subtle deception such as strategically phrasing and intentionally manipulating information to misguide and deceive other agents.
InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?
Task performance and fairness scores of LLaMA and LLaMA--2 models indicate that the proposed $LSS_{\beta}$ metric can effectively determine the readiness of a model for safe usage in the legal sector.
LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition using Graph Neural Networks
To overcome these limitations, we propose novel line conversation graph convolutional network (LineConGCN) and graph attention (LineConGAT) models for ERC analysis.
Multi-Agent Learning of Efficient Fulfilment and Routing Strategies in E-Commerce
This paper presents an integrated algorithmic framework for minimising product delivery costs in e-commerce (known as the cost-to-serve or C2S).
PolicyClusterGCN: Identifying Efficient Clusters for Training Graph Convolutional Networks
Specifically, the subgraph-based sampling approaches such as ClusterGCN and GraphSAINT have achieved state-of-the-art performance on the node classification tasks.
GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts
We propose a novel approach that uses a generative adversarial network (GAN) to minimize the Jensen-Shannon divergence between the state-trajectory distributions of the demonstrator and the imitator.
Clustering Indices based Automatic Classification Model Selection
We also propose an end-to-end Automated ML system for data classification based on our model selection method.
MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learning
Unlike existing models, MABL is capable of encoding essential global information into the latent states during training while guaranteeing the decentralized execution of learned policies.
Are Models Trained on Indian Legal Data Fair?
We highlight the propagation of learnt algorithmic biases in the bail prediction task for models trained on Hindi legal documents.
Physics-Informed Model-Based Reinforcement Learning
In these environments, the physics-informed version of our algorithm achieves significantly better average-return and sample efficiency.
ReGrAt: Regularization in Graphs using Attention to handle class imbalance
Changing data composition is a popular way to address the imbalance in node classification.
GrabQC: Graph based Query Contextualization for automated ICD coding
We propose to automate this manual process by automatically constructing a query for the IR system using the entities auto-extracted from the clinical notes.
Multi-Variate Time Series Forecasting on Variable Subsets
Through systematic experiments across 4 datasets and 5 forecast models, we show that our technique is able to recover close to 95\% performance of the models even when only 15\% of the original variables are present.
Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space.
Evolutionary Approach to Security Games with Signaling
Green Security Games have become a popular way to model scenarios involving the protection of natural resources, such as wildlife.
A Survey of Adversarial Defences and Robustness in NLP
In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack.
A Causal Approach for Unfair Edge Prioritization and Discrimination Removal
We prove this result for the non-trivial non-parametric model setting when the cumulative unfairness cannot be expressed in terms of edge unfairness.
Smooth Imitation Learning via Smooth Costs and Smooth Policies
We call our new smooth IL algorithm \textit{Smooth Policy and Cost Imitation Learning} (SPaCIL, pronounced 'Special').
Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis
Synthesizing high-quality, realistic images from text-descriptions is a challenging task, and current methods synthesize images from text in a multi-stage manner, typically by first generating a rough initial image and then refining image details at subsequent stages.
Dynamic probabilistic logic models for effective abstractions in RL
State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments.
Semi-Supervised Deep Learning for Multiplex Networks
Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer.
Causal Contextual Bandits with Targeted Interventions
We study a contextual bandit setting where the learning agent has the ability to perform interventions on targeted subsets of the population, apart from possessing qualitative causal side-information.
A Joint Training Framework for Open-World Knowledge Graph Embeddings
However, we find that existing approaches suffer from one or more of four drawbacks – 1) They are not modular with respect to the choice of the KG embedding model 2) They ignore best practices for aligning two embedding spaces 3) They do not account for differences in training strategy needed when presented with datasets with different description sizes and 4) They do not produce entity embeddings for use by downstream tasks.
TAG: Task-based Accumulated Gradients for Lifelong learning
We also show that our method performs better than several state-of-the-art methods in lifelong learning on complex datasets with a large number of tasks.
Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes
India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100, 000 live births.
Hyperedge Prediction using Tensor Eigenvalue Decomposition
This is further used to propose a hyperedge prediction algorithm.
Neural Fitted Q Iteration based Optimal Bidding Strategy in Real Time Reactive Power Market_1
In this paper, a pioneer work on learning optimal bidding strategies from observation and experience in a three-stage reactive power market is reported.
qRRT: Quality-Biased Incremental RRT for Optimal Motion Planning in Non-Holonomic Systems
This paper presents a sampling-based method for optimal motion planning in non-holonomic systems in the absence of known cost functions.
Reinforcement Learning for Unified Allocation and Patrolling in Signaling Games with Uncertainty
We therefore first propose a novel GSG model that combines defender allocation, patrolling, real-time drone notification to human patrollers, and drones sending warning signals to attackers.
Decision Making
Multiagent Systems
Relational Boosted Bandits
Contextual bandits algorithms have become essential in real-world user interaction problems in recent years.
Hypergraph Partitioning using Tensor Eigenvalue Decomposition
We also show improvement for the min-cut solution on 2-uniform hypergraphs (graphs) over the standard spectral partitioning algorithm.
Goal directed molecule generation using Monte Carlo Tree Search
One challenging and essential task in biochemistry is the generation of novel molecules with desired properties.
MADRaS : Multi Agent Driving Simulator
In this work, we present MADRaS, an open-source multi-agent driving simulator for use in the design and evaluation of motion planning algorithms for autonomous driving.
Reinforcement Learning for Improving Object Detection
The performance of a trained object detection neural network depends a lot on the image quality.
A Causal Linear Model to Quantify Edge Flow and Edge Unfairness for UnfairEdge Prioritization and Discrimination Removal
Unlike previous works that only make cautionary claims of discrimination and de-biases data after its generation, this paper attempts to prioritize unfair sources before mitigating their unfairness in the real-world.
Missed calls, Automated Calls and Health Support: Using AI to improve maternal health outcomes by increasing program engagement
India accounts for 11% of maternal deaths globally where a woman dies in childbirth every fifteen minutes.
Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains
This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains.
On Incorporating Structural Information to improve Dialogue Response Generation
This requires capturing structural, sequential and semantic information from the conversation context and the background resources.
Understanding Dynamic Scenes using Graph Convolution Networks
We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera.
Ranked #1 on
Test results
on KITTI
Towards Transparent and Explainable Attention Models
To make attention mechanisms more faithful and plausible, we propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse.
EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks
Our results indicate that EMPIR boosts the average adversarial accuracies by 42. 6%, 15. 2% and 10. 5% for the DNN models trained on the MNIST, CIFAR-10 and ImageNet datasets respectively, when compared to single full-precision models, without sacrificing accuracy on the unperturbed inputs.
A Unified Non-Negative Matrix Factorization Framework for Semi-Supervised Learning on Graphs
We propose a Semi-Supervised Learning (SSL) methodology that explicitly encodes different necessary priors to learn efficient representations for nodes in a network.
Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks
Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity.
SEERL: Sample Efficient Ensemble Reinforcement Learning
However, ensemble methods are relatively less popular in reinforcement learning owing to the high sample complexity and computational expense involved in obtaining a diverse ensemble.
Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems
This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research.
Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent.
Let's Ask Again: Refine Network for Automatic Question Generation
It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer.
Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling
A serious challenge when finding influential actors in real-world social networks is the lack of knowledge about the structure of the underlying network.
ExTra: Transfer-guided Exploration
Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment.
Learning Interpretable Models Using Uncertainty Oracles
Additionally, we show that (1) it is more accurate than its predecessor, (2) requires only one hyperparameter to be set in practice, (3) accommodates a multi-variate notion of model size, e. g., both maximum depth of a tree and number of trees in Gradient Boosted Models, and (4) works across different feature spaces between the uncertainty oracle and the interpretable model, e. g., a GRU might act as an oracle for a decision tree that ingests n-grams.
MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion.
Successor Options: An Option Discovery Framework for Reinforcement Learning
This work adopts a complementary approach, where we attempt to discover options that navigate to landmark states.
Interpretability with Accurate Small Models
Our technique identifies the training data distribution to learn from that leads to the highest accuracy for a model of a given size.
Network Representation Learning: Consolidation and Renewed Bearing
An important area of research that has emerged over the last decade is the use of graphs as a vehicle for non-linear dimensionality reduction in a manner akin to previous efforts based on manifold learning with uses for downstream database processing, machine learning and visualization.
Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning
On top of our LSTM neural network that learnt musical sequences in this representation, we built an RL agent that learnt to find combinations of songs whose joint dominance produced pleasant compositions.
An Active Learning Framework for Efficient Robust Policy Search
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters.
Hypergraph Clustering: A Modularity Maximization Approach
Clustering on hypergraphs has been garnering increased attention with potential applications in network analysis, VLSI design and computer vision, among others.
Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning
In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.
Learning to Prevent Monocular SLAM Failure using Reinforcement Learning
Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment.
Robotics
Discovering hierarchies using Imitation Learning from hierarchy aware policies
Learning options that allow agents to exhibit temporally higher order behavior has proven to be useful in increasing exploration, reducing sample complexity and for various transfer scenarios.
Successor Options : An Option Discovery Algorithm for Reinforcement Learning
Additionally, we describe an Incremental Successor options model that iteratively builds options and explores in environments where exploration through primitive actions is inadequate to form the Successor Representations.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Improvements on Hindsight Learning
One such approach is Hindsight Experience replay which uses an off-policy Reinforcement Learning algorithm to learn a goal conditioned policy.
Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing
Based on these observations, we propose Pack and Detect (PaD), an approach to reduce the computational requirements of object detection in videos.
HOPF: Higher Order Propagation Framework for Deep Collective Classification
Given a graph where every node has certain attributes associated with it and some nodes have labels associated with them, Collective Classification (CC) is the task of assigning labels to every unlabeled node using information from the node as well as its neighbors.
Fusion Graph Convolutional Networks
State-of-the-art models for node classification on such attributed graphs use differentiable recursive functions that enable aggregation and filtering of neighborhood information from multiple hops.
Language Expansion In Text-Based Games
Text-based games are suitable test-beds for designing agents that can learn by interaction with the environment in the form of natural language text.
DiGrad: Multi-Task Reinforcement Learning with Shared Actions
In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continuous action spaces, which we call as DiGrad (Differential Policy Gradient).
Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks
In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.
Rate of Change Analysis for Interestingness Measures
We present a comprehensive analysis of 50 interestingness measures and classify them in accordance with the two properties.
Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates
We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting.
Shared Learning : Enhancing Reinforcement in $Q$-Ensembles
Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward.
RAIL: Risk-Averse Imitation Learning
Generative Adversarial Imitation Learning (GAIL) is a state-of-the-art algorithm for learning policies when the expert's behavior is available as a fixed set of trajectories.
Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning
Our second major contribution is that we propose a generalization of lambda-returns called Confidence-based Autodidactic Returns (CAR), wherein the RL agent learns the weighting of the n-step returns in an end-to-end manner.
Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning
Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains.
Diversity driven Attention Model for Query-based Abstractive Summarization
Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion.
Ranked #2 on
Query-Based Extractive Summarization
on Debatepedia
Thresholding Bandits with Augmented UCB
In this paper we propose the Augmented-UCB (AugUCB) algorithm for a fixed-budget version of the thresholding bandit problem (TBP), where the objective is to identify a set of arms whose quality is above a threshold.
DyVEDeep: Dynamic Variable Effort Deep Neural Networks
Complementary to these approaches, DyVEDeep is a dynamic approach that exploits the heterogeneity in the inputs to DNNs to improve their compute efficiency with comparable classification accuracy.
Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning
Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it.
Learning to Multi-Task by Active Sampling
In this work, we propose an efficient multi-task learning framework which solves multiple goal-directed tasks in an on-line setup without the need for expert supervision.
Exploration for Multi-task Reinforcement Learning with Deep Generative Models
Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP.
EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks.
Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering
This paper introduces an automated skill acquisition framework in reinforcement learning which involves identifying a hierarchical description of the given task in terms of abstract states and extended actions between abstract states.
Dynamic Frame skip Deep Q Network
Deep Reinforcement Learning methods have achieved state of the art performance in learning control policies for the games in the Atari 2600 domain.
Linear Bandit algorithms using the Bootstrap
One of the proposed methods, X-Random bootstrap, performs better than the baselines in-terms of cumulative regret across various degrees of noise and different number of trials.
Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
In this work, we address a real-world scenario where no direct parallel data is available between two views of interest (say, $V_1$ and $V_2$) but parallel data is available between each of these views and a pivot view ($V_3$).
Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task.
TSEB: More Efficient Thompson Sampling for Policy Learning
In this paper, we propose TSEB, a Thompson Sampling based algorithm with adaptive exploration bonus that aims to solve the problem with tighter PAC guarantees, while being cautious on the regret as well.
A Reinforcement Learning Approach to Online Learning of Decision Trees
Online decision tree learning algorithms typically examine all features of a new data point to update model parameters.
Correlational Neural Networks
CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace.
An Autoencoder Approach to Learning Bilingual Word Representations
Cross-language learning allows us to use training data from one language to build models for a different language.
