Search Results for author:
Found 41 papers, 4 papers with code
Less Is More - On the Importance of Sparsification for Transformers and Graph Neural Networks for TSP
Furthermore, we propose ensembles of different sparsification levels allowing models to focus on the most promising parts while also allowing information flow between all nodes of a TSP instance.
Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward
We develop a deep reinforcement learning framework for tactical decision making in an autonomous truck, specifically for Adaptive Cruise Control (ACC) and lane change maneuvers in a highway scenario.
Tree Ensembles for Contextual Bandits
We propose a novel framework for contextual multi-armed bandits based on tree ensembles.
Effective Acquisition Functions for Active Correlation Clustering
Correlation clustering is a powerful unsupervised learning paradigm that supports positive and negative similarities.
Combinatorial Gaussian Process Bandits in Bayesian Settings: Theory and Application for Energy-Efficient Navigation
We consider a combinatorial Gaussian process semi-bandit problem with time-varying arm availability.
Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach
In this paper, we provide a novel formulation of the online decision making problem based on combinatorial multi-armed bandits and take the (possibly stochastic) cost of performing tests into account.
Efficient Online Decision Tree Learning with Active Feature Acquisition
Specifically, we employ a surrogate information acquisition function based on adaptive submodularity to actively query feature values with a minimal cost, while using a posterior sampling scheme to maintain a low regret for online prediction.
A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Prediction
Then, we convert the tree representation of the source code to a Flow Augmented-AST graph (FA-AST) representation.
Utilizing Reinforcement Learning for de novo Drug Design
Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years.
Prediction of Time and Distance of Trips Using Explainable Attention-based LSTMs
Finally, the last model is based on two parallel At-LSTMs, where similarly, each At-LSTM predicts time and distance separately through fully connected layers.
Correlation Clustering with Active Learning of Pairwise Similarities
Correlation clustering is a well-known unsupervised learning setting that deals with positive and negative pairwise similarities.
A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles
In this work, we address the problem of long-distance navigation for battery electric vehicles (BEVs), where one or more charging sessions are required to reach the intended destination.
Online Learning Models for Vehicle Usage Prediction During COVID-19
One way to mitigate these issues is by performing battery thermal preconditioning, which increases the energy efficiency of the battery.
TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networks
TEP-GNN uses FA-ASTs, or flow-augmented ASTs, as a graph-based code representation approach, and predicts test execution times using a powerful graph neural network (GNN) deep learning model.
Autonomous Drug Design with Multi-Armed Bandits
Recent developments in artificial intelligence and automation support a new drug design paradigm: autonomous drug design.
A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification
Bottleneck identification is a challenging task in network analysis, especially when the network is not fully specified.
Passive and Active Learning of Driver Behavior from Electric Vehicles
To address the first challenge, passive learning of driver behavior, we investigate non-recurrent architectures such as self-attention models and convolutional neural networks with joint recurrence plots (JRP), and compare them with recurrent models.
Deep Q-learning: a robust control approach
The role of the target network is overtaken by the control input, which also exploits the temporal dependency of samples (opposed to a randomized memory buffer).
Online Learning of Energy Consumption for Navigation of Electric Vehicles
In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound.
Shift of Pairwise Similarities for Data Clustering
Several clustering methods (e. g., Normalized Cut and Ratio Cut) divide the Min Cut cost function by a cluster dependent factor (e. g., the size or the degree of the clusters), in order to yield a more balanced partitioning.
Online Learning of Network Bottlenecks via Minimax Paths
In this paper, we study bottleneck identification in networks via extracting minimax paths.
Active Learning of Driving Scenario Trajectories
In this study, we develop a generic active learning framework to annotate driving trajectory time series data.
Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based Approach
This paper presents a constrained policy gradient algorithm.
A Unified Framework for Online Trip Destination Prediction
In this paper, we present a unified framework for trip destination prediction in an online setting, which is suitable for both online training and online prediction.
A Generic Framework for Clustering Vehicle Motion Trajectories
The development of autonomous vehicles requires having access to a large amount of data in the concerning driving scenarios.
Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks
v) We investigate how active learning with neural networks can benefit from pseudo-labels as proxies for actual labels.
A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories
Second, we develop an architecture based on Recurrent Autoencoder with GANs to obviate the variable length issue, wherein we train a GAN to learn/generate the latent representations of original trajectories.
Efficient Optimization of Dominant Set Clustering with Frank-Wolfe Algorithms
We study Frank-Wolfe algorithms - standard, pairwise, and away-steps - for efficient optimization of Dominant Set Clustering.
Memory-Efficient Sampling for Minimax Distance Measures
Minimax distance measure extracts the underlying patterns and manifolds in an unsupervised manner.
Analysis of Knowledge Transfer in Kernel Regime
Knowledge transfer is shown to be a very successful technique for training neural classifiers: together with the ground truth data, it uses the "privileged information" (PI) obtained by a "teacher" network to train a "student" network.
Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction
Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature.
Ranked #1 on
Image Classification
on N-MNIST
An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles
In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound.
Hierarchical Correlation Clustering and Tree Preserving Embedding
We propose a hierarchical correlation clustering method that extends the well-known correlation clustering to produce hierarchical clusters applicable to both positive and negative pairwise dissimilarities.
Lifelong Learning Starting From Zero
We present a deep neural-network model for lifelong learning inspired by several forms of neuroplasticity.
Do Kernel and Neural Embeddings Help in Training and Generalization?
The approximated representations induced by these kernels are fed to the neural network and the optimization and generalization properties of the final model are evaluated and compared.
Unsupervised Representation Learning with Minimax Distance Measures
We investigate the use of Minimax distances to extract in a nonparametric way the features that capture the unknown underlying patterns and structures in the data.
Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework
We develop a novel theoretical framework for understating OT schemes respecting a class structure.
Trip Prediction by Leveraging Trip Histories from Neighboring Users
We propose a novel approach for trip prediction by analyzing user's trip histories.
Learning Representations from Dendrograms
Then, to address the model selection problem, we study the aggregation of different dendrogram-based distances respectively in solution space and in representation space in the spirit of deep representations.
Reliable Agglomerative Clustering
Standard agglomerative clustering suggests establishing a new reliable linkage at every step.
Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting
We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes.
