Related papers: Autodeleveraging as Online Learning

We consider online imitation learning (OIL), where the task is to find a policy that imitates the behavior of an expert via active interaction with the environment. We aim to bridge the gap between the theory and practice of policy…

Deep neural networks (DNNs) are often trained on the premise that the complete training data set is provided ahead of time. However, in real-world scenarios, data often arrive in chunks over time. This leads to important considerations…

Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a…

Deep learning is the method of choice for trajectory prediction for autonomous vehicles. Unfortunately, its data-hungry nature implicitly requires the availability of sufficiently rich and high-quality centralized datasets, which easily…

We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of…

Automatic bill payment is an important part of business operations in fintech companies. The practice of deduction was mainly based on the total amount or heuristic search by dividing the bill into smaller parts to deduct as much as…

Decentralized federated learning (DFL) enables clients (e.g., hospitals and banks) to jointly train machine learning models without a central orchestration server. In each global training round, each client trains a local model on its own…

Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In practice, pronounced concept drift compounded by significant label verification latency…

Federated Learning (FL) can be used in mobile edge networks to train machine learning models in a distributed manner. Recently, FL has been interpreted within a Model-Agnostic Meta-Learning (MAML) framework, which brings FL significant…

Anomaly detection in decision-making sequences is a challenging problem due to the complexity of normality representation learning and the sequential nature of the task. Most existing methods based on Reinforcement Learning (RL) are…

In the realm of edge computing, the increasing demand for high Quality of Service (QoS), particularly in dynamic multimedia streaming applications (e.g., Augmented Reality/Virtual Reality and online gaming), has prompted the need for…

In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled…

We study the online problem of minimizing power consumption in systems with multiple power-saving states. During idle periods of unknown lengths, an algorithm has to choose between power-saving states of different energy consumption and…

Omnipredictors are simple prediction functions that encode loss-minimizing predictions with respect to a hypothesis class $H$, simultaneously for every loss function within a class of losses $L$. In this work, we give near-optimal learning…

In [1, 2], we have explored the theoretical aspects of feature extraction optimization processes for solving largescale problems and overcoming machine learning limitations. Majority of optimization algorithms that have been introduced in…

In this paper, the inverse reinforcement learning (IRL) problem is addressed to reconstruct the unknown cost function underlying an observed optimal policy in a model-free manner, whose online adaptation with completely off-policy system…

Distributed machine learning (ML) at network edge is a promising paradigm that can preserve both network bandwidth and privacy of data providers. However, heterogeneous and limited computation and communication resources on edge servers (or…

Off-policy, value-based reinforcement learning methods such as Q-learning are appealing because they can learn from arbitrary experience, including data collected by older policies or other agents. In practice, however, bootstrapping makes…

Decentralized Exchanges (DEXs) are new types of marketplaces leveraging Blockchain technology. They allow users to trade assets with Automatic Market Makers (AMM), using funds provided by liquidity providers, removing the need for order…

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…