Search Results for author:
Found 19 papers, 4 papers with code
Q2R: A Query-to-Resolution System for Natural-Language Queries
We present a system for document retrieval that combines direct classification with standard content-based retrieval approaches to significantly improve the relevance of the retrieved documents.
Efficiently Distilling LLMs for Edge Applications
Supernet training of LLMs is of great interest in industrial applications as it confers the ability to produce a palette of smaller models at constant cost, regardless of the number of models (of different size / latency) produced.
Transfer-Once-For-All: AI Model Optimization for Edge
Hence, we propose Transfer-Once-For-All (TOFA) for supernet-style training on small data sets with constant computational training cost over any number of edge deployment scenarios.
Neural-Progressive Hedging: Enforcing Constraints in Reinforcement Learning with Stochastic Programming
We propose a framework, called neural-progressive hedging (NP), that leverages stochastic programming during the online phase of executing a reinforcement learning (RL) policy.
Order Constraints in Optimal Transport
Optimal transport is a framework for comparing measures whereby a cost is incurred for transporting one measure to another.
Decentralized Deterministic Multi-Agent Reinforcement Learning
We extend those results to offer a provably-convergent decentralized actor-critic algorithm for learning deterministic policies on continuous action spaces.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning
One of the main challenges in real-world reinforcement learning is to learn successfully from limited training samples.
Probabilistic Inference for Learning from Untrusted Sources
Federated learning brings potential benefits of faster learning, better solutions, and a greater propensity to transfer when heterogeneous data from different parties increases diversity.
Robustness and Personalization in Federated Learning: A Unified Approach via Regularization
We present a class of methods for robust, personalized federated learning, called Fed+, that unifies many federated learning algorithms.
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
Variational Bayesian Inference for Crowdsourcing Predictions
Crowdsourcing has emerged as an effective means for performing a number of machine learning tasks such as annotation and labelling of images and other data sets.
A Deep Ensemble Multi-Agent Reinforcement Learning Approach for Air Traffic Control
Air traffic control is an example of a highly challenging operational problem that is readily amenable to human expertise augmentation via decision support technologies.
FASTER: Fusion AnalyticS for public Transport Event Response
Increasing urban concentration raises operational challenges that can benefit from integrated monitoring and decision support.
High-frequency crowd insights for public safety and congestion control
We present results from several projects aimed at enabling the real-time understanding of crowds and their behaviour in the built environment.
Robust commuter movement inference from connected mobile devices
The preponderance of connected devices provides unprecedented opportunities for fine-grained monitoring of the public infrastructure.
Towards Robust ResNet: A Small Step but A Giant Leap
Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization.
A Probabilistic Model of the Bitcoin Blockchain
The Bitcoin transaction graph is a public data structure organized as transactions between addresses, each associated with a logical entity.
Characterizing Entities in the Bitcoin Blockchain
Bitcoin has created a new exchange paradigm within which financial transactions can be trusted without an intermediary.
Smooth Inter-layer Propagation of Stabilized Neural Networks for Classification
Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification.
