Related papers: Cross-Layer Effects on Training Neural Algorithms …
This paper proposes a deep reinforcement learning-based video streaming scheme for mobility-aware vehicular networks, e.g., vehicles on the highway. We consider infrastructure-assisted and mmWave-based scenarios in which the macro base…
Training deep neural networks is challenging. To accelerate training and enhance performance, we propose PadamP, a novel optimization algorithm. PadamP is derived by applying the adaptive estimation of the p-th power of the second-order…
Despite impressive advancements in Autonomous Driving Systems (ADS), navigation in complex road conditions remains a challenging problem. There is considerable evidence that evaluating the subjective risk level of various decisions can…
In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an…
Nowadays, online learning is an appealing learning paradigm, which is of great interest in practice due to the recent emergence of large scale applications such as online advertising placement and online web ranking. Standard online…
Online event-based perception techniques on board robots navigating in complex, unstructured, and dynamic environments can suffer unpredictable changes in the incoming event rates and their processing times, which can cause computational…
Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case…
This paper presents a cross-layer video delivery scheme, StreamOptix, and proposes a joint optimization algorithm for video delivery that leverages the characteristics of the physical (PHY), medium access control (MAC), and application…
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…
With the demand to process ever-growing data volumes, a variety of new data stream processing frameworks have been developed. Moving an implementation from one such system to another, e.g., for performance reasons, requires adapting…
The Asynchronous Transfer Mode (ATM) networks are quickly being adopted as backbones over various parts of the Internet. This paper analyzes the performance of TCP/IP protocols over ATM network's Available Bit Rate (ABR) and Unspecified Bit…
Adaptive bitrate (ABR) streaming is the de facto solution for achieving smooth viewing experiences under unstable network conditions. However, most of the existing rate adaptation approaches for ABR are content-agnostic, without considering…
Recently, HTTP streaming has become very popular for delivering video over the Internet. For adaptivity, a provider should generate multiple versions of a video as well as the related metadata. Various adaptation methods have been proposed…
We consider the jointly optimal design of a transmission scheduling and admission control policy for adaptive video streaming over small cell networks. We formulate the problem as a dynamic network utility maximization and observe that it…
Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…
The emergence of video applications and video capable devices have contributed substantially to the increase of video traffic on Internet. New mechanisms recommending video rate adaptation towards delivering enhanced Quality of Experience…
Emerging applications of machine learning in numerous areas involve continuous gathering of and learning from streams of data. Real-time incorporation of streaming data into the learned models is essential for improved inference in these…
Immersive video offers the freedom to navigate inside virtualized environment. Instead of streaming the bulky immersive videos entirely, a viewport (also referred to as field of view, FoV) adaptive streaming is preferred. We often stream…
In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since…
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a…