Search Results for author:
Found 35 papers, 12 papers with code
CUER: Corrected Uniform Experience Replay for Off-Policy Continuous Deep Reinforcement Learning Algorithms
The utilization of the experience replay mechanism enables agents to effectively leverage their experiences on several occasions.
Binary Feature Mask Optimization for Feature Selection
However, no study has introduced a training-free framework for a generic ML model to select features while considering the importance of the feature subsets as a whole, instead of focusing on the individual features.
AFS-BM: Enhancing Model Performance through Adaptive Feature Selection with Binary Masking
In particular, we do the joint optimization and binary masking to continuously adapt the set of features and model parameters during the training process.
Hierarchical Ensemble-Based Feature Selection for Time Series Forecasting
This hierarchical structure allows for flexible depth and feature selection.
Hybrid State Space-based Learning for Sequential Data Prediction with Joint Optimization
We achieve this by introducing novel state space representations for the base models, which are then combined to provide a full state space representation of the hybrid or the ensemble.
Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI
We introduce a novel deep reinforcement learning (DRL) approach to jointly optimize transmit beamforming and reconfigurable intelligent surface (RIS) phase shifts in a multiuser multiple input single output (MU-MISO) system to maximize the sum downlink rate under the phase-dependent reflection amplitude model.
Deep Intrinsically Motivated Exploration in Continuous Control
In continuous control, exploration is often performed through undirected strategies in which parameters of the networks or selected actions are perturbed by random noise.
Actor Prioritized Experience Replay
A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error.
Optimal Tracking in Prediction with Expert Advice
We study the prediction with expert advice setting, where the aim is to produce a decision by combining the decisions generated by a set of experts, e. g., independently running algorithms.
Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach
Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data.
Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms
Learning in high dimensional continuous tasks is challenging, mainly when the experience replay memory is very limited.
A Hybrid Framework for Sequential Data Prediction with End-to-End Optimization
We investigate nonlinear prediction in an online setting and introduce a hybrid model that effectively mitigates, via an end-to-end architecture, the need for hand-designed features and manual model selection issues of conventional nonlinear prediction/regression methods.
AWD3: Dynamic Reduction of the Estimation Bias
We show through continuous control environments of OpenAI gym that our algorithm matches or outperforms the state-of-the-art off-policy policy gradient learning algorithms.
Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay
In addition, experience replay stores the transitions are generated by the previous policies of the agent that may significantly deviate from the most recent policy of the agent.
Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods
We show that in deep actor-critic methods that aim to overcome the overestimation bias, if the reinforcement signals received by the agent have a high variance, a significant underestimation bias arises.
PySAD: A Streaming Anomaly Detection Framework in Python
PySAD is an open-source python framework for anomaly detection on streaming data.
Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences.
Spatio-temporal Sequence Prediction with Point Processes and Self-organizing Decision Trees
We study the spatio-temporal prediction problem and introduce a novel point-process-based prediction algorithm.
A Tree Architecture of LSTM Networks for Sequential Regression with Missing Data
In our architecture, we employ a variable number of LSTM networks, which use only the existing inputs in the sequence, in a tree-like architecture without any statistical assumptions or imputations on the missing data, unlike all the previous approaches.
Achieving Online Regression Performance of LSTMs with Simple RNNs
Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies.
Unsupervised Anomaly Detection via Deep Metric Learning with End-to-End Optimization
We investigate unsupervised anomaly detection for high-dimensional data and introduce a deep metric learning (DML) based framework.
RNN-based Online Learning: An Efficient First-Order Optimization Algorithm with a Convergence Guarantee
We investigate online nonlinear regression with continually running recurrent neural network networks (RNNs), i. e., RNN-based online learning.
Stability of the Decoupled Extended Kalman Filter Learning Algorithm in LSTM-Based Online Learning
We investigate the convergence and stability properties of the decoupled extended Kalman filter learning algorithm (DEKF) within the long-short term memory network (LSTM) based online learning framework.
Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays
To construct our algorithm, we introduce a new expert advice algorithm for the multiple-play setting.
An Efficient and Effective Second-Order Training Algorithm for LSTM-based Adaptive Learning
We study adaptive (or online) nonlinear regression with Long-Short-Term-Memory (LSTM) based networks, i. e., LSTM-based adaptive learning.
Universal Online Convex Optimization with Minimax Optimal Second-Order Dynamic Regret
Our approach can compete against all comparator sequences simultaneously (universally) in a minimax optimal manner, i. e. each regret guarantee depends on the respective comparator path variation.
Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under Sub-Gradient Observation Failures
We specifically study scenarios where our sub-gradient observations can be noisy or even completely missing in a stochastic manner.
Highly Efficient Hierarchical Online Nonlinear Regression Using Second Order Methods
We introduce highly efficient online nonlinear regression algorithms that are suitable for real life applications.
An Asymptotically Optimal Contextual Bandit Algorithm Using Hierarchical Structures
Therefore, we design our algorithms based on the optimal adaptive combination and asymptotically achieve the performance of the best mapping as well as the best arm selection policy.
Team-Optimal Distributed MMSE Estimation in General and Tree Networks
Finally, in the numerical examples, we demonstrate the superior performance of the introduced algorithms in the finite-horizon MSE sense due to optimal estimation.
Data Imputation through the Identification of Local Anomalies
We introduce a comprehensive and statistical framework in a model free setting for a complete treatment of localized data corruptions due to severe noise sources, e. g., an occluder in the case of a visual recording.
Predicting Nearly As Well As the Optimal Twice Differentiable Regressor
We study nonlinear regression of real valued data in an individual sequence manner, where we provide results that are guaranteed to hold without any statistical assumptions.
A Novel Family of Adaptive Filtering Algorithms Based on The Logarithmic Cost
We introduce important members of this family of algorithms such as the least mean logarithmic square (LMLS) and least logarithmic absolute difference (LLAD) algorithms that improve the convergence performance of the conventional algorithms.
A Unified Approach to Universal Prediction: Generalized Upper and Lower Bounds
We first introduce the lower bounds on this relative performance in the mixture of experts framework, where we show that for any sequential algorithm, there always exists a sequence for which the performance of the sequential algorithm is lower bounded by zero.
A Comprehensive Approach to Universal Piecewise Nonlinear Regression Based on Trees
In this paper, we investigate adaptive nonlinear regression and introduce tree based piecewise linear regression algorithms that are highly efficient and provide significantly improved performance with guaranteed upper bounds in an individual sequence manner.
