This work explores Target Networks and Functional Regularization in deep Reinforcement Learning.
problem Stability and performance issues in deep Reinforcement Learning due to target value instability.
method Proposes and studies an explicit Functional Regularization approach as a replacement for Target Networks.
result Functional Regularization improves performance and stability compared to Target Networks.
The paper analyzes an actor-critic algorithm with target networks for deep reinforcement learning.
problem Lack of theoretical understanding of target networks in actor-critic methods.
method Proposes a theoretical analysis of an online target-based actor-critic algorithm with linear function approximation.
result Establishes asymptotic convergence results and finite-time analysis for both critic and actor.
Target encoding is an effective technique to deliver better performance for conventional machine learning methods, and recently, for deep neural networks as well. However, the existing target encoding approaches require significant increase in the learning capacity, thus demand higher computation power and more trainin…
Calibrates network confidence for unsupervised domain adaptation.
problem Calibrating a model trained on a source domain to a target domain without labeled data.
method Estimates network accuracy on the target domain and calibrates prediction confidence directly in the target domain.
result Significantly outperforms existing methods across standard datasets.
This paper studies how to compress neural networks while maintaining accuracy.
problem Compressing a two-layer neural network with fewer nodes without losing accuracy.
method Using tools from high-dimensional probability, the authors minimize the L_2 loss between the target and compressed networks.
result The error rate of the approximation is shown as a function of input dimension and network size in the mean-field limit.
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to…
With the increasing variety of services that e-commerce platforms provide, criteria for evaluating their success become also increasingly multi-targeting. This work introduces a multi-target optimization framework with Bayesian modeling of the target events, called Deep Bayesian Multi-Target Learning (DBMTL). In this f…
The paper proposes a neural network architecture inspired by Langevin Monte Carlo for sampling from target distributions.
problem Sampling from complex target distributions efficiently.
method A neural network architecture inspired by Langevin Monte Carlo is proposed to map samples from a simple reference distribution to samples from the target.
result The proposed neural network architecture achieves approximation rates in the Wasserstein-2 distance for smooth, log-concave target distributions.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
New method targets sparsity to prevent overfitting in deep nets.
problem Overfitting in deep neural networks with small datasets.
method Targeted sparsity regularization to visualize and counteract overfitting.
result Significant increase in image classification performance without overfitting.
Sharp theory of neural network scaling laws for hierarchical targets.
problem Learning hierarchical multi-index models in neural networks.
method Sharp information-theoretic scaling laws derived for two-layer neural networks.
result Optimal rates achieved by a simple spectral estimator.
Randomly initialized networks contain subnetworks that perform similarly to target networks.
problem Proving the lottery ticket hypothesis for neural networks.
method Pruning over-parameterized neural networks to find subnetworks.
result Randomly initialized networks contain subnetworks with similar performance to target networks without additional training.
GAIT-prop derives a biologically plausible learning rule from backpropagation.
problem Biological implausibility in traditional backpropagation for neural networks.
method GAIT-prop uses a top-down model to convert output error into plausible targets for weight updates.
result GAIT-prop and backpropagation give identical weight updates under certain conditions.
This work analyzes how often to update the target network in Q-learning.
problem Understanding the optimal frequency of target network updates in Q-learning.
method Formulated target updates as a nested optimization scheme, derived finite-time convergence analysis.
result Optimal target update frequency increases geometrically over time.
In target tracking, the estimation of an unknown weaving target frequency is crucial for improving the miss distance. The estimation process is commonly carried out in a Kalman framework. The objective of this paper is to examine the potential of using neural networks in target tracking applications. To that end, we pr…
The paper proposes a method for valid multi-target regression predictions.
problem Valid multi-variate predictions for multi-target regression.
method Copula functions applied to deep neural networks for inductive conformal prediction.
result The proposed method ensures efficiency and validity for multi-target regression problems.
GEFA predicts drug-target affinity using graph neural networks.
problem Accurate prediction of drug-target interactions for rapid drug repurposing.
method GEFA (Graph Early Fusion Affinity) is a novel graph-in-graph neural network with attention mechanism.
result GEFA effectively models drug-target interactions, demonstrating the effectiveness of pre-trained protein embedding and nested graph representation.
The task of unsupervised domain adaptation is proposed to transfer the knowledge of a label-rich domain (source domain) to a label-scarce domain (target domain). Matching feature distributions between different domains is a widely applied method for the aforementioned task. However, the method does not perform well whe…
PQ-learning improves Q-learning by periodically updating target estimates.
problem Improving sample complexity in Q-learning for finding optimal policies.
method Maintains two Q-value estimates, one online and one target, updated periodically.
result PQ-learning achieves better sample complexity for finding epsilon-optimal policies.
New findings show depth is more important than width in neural networks.
problem Understanding the role of width and depth in neural networks.
method Constructed networks with bounded weights and width at most d+2, showing depth plays a more significant role.
result Depth is more important than width in the expressive power of neural networks.
Machine learning models are vulnerable to adversarial examples. An adversary modifies the input data such that humans still assign the same label, however, machine learning models misclassify it. Previous approaches in the literature demonstrated that adversarial examples can even be generated for the remotely hosted m…
The Long Short-Term Memory (LSTM) neural network based data association algorithm named as DeepDA for multi-target tracking in clutters is proposed to deal with the NP-hard combinatorial optimization problem in this paper. Different from the classical data association methods involving complex models and accurate prior…
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) …
We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outp…
This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs). The approach is based on two principles: (a) if the source randomness of the network is a continuous distribution (the "semi-discrete" setting), th…
This work explores how neural network architecture affects robustness to noisy labels.
problem The impact of neural network architecture on robustness to noisy labels.
method Formal framework connecting robustness to architecture alignments, measured by predictive power in representations.
result Network robustness to noisy labels improves when its architecture is more aligned with the target function.
The paper investigates how target normalization and momentum affect dying ReLUs in neural networks.
problem Understanding and mitigating the dying ReLU problem in neural networks.
method Empirical analysis and theoretical modeling of a discrete-time linear autonomous system.
result Target variance plays a crucial role in the dying ReLU phenomenon, and momentum exacerbates this issue.
Proves existence of optimal shallow neural networks with ReLU activation.
problem Proving the existence of optimal shallow feedforward networks with ReLU activation.
method Proves existence of global minima in the loss landscape for continuous target functions using shallow feedforward neural networks with ReLU activation.
result Existence of global minima in the loss landscape for shallow feedforward networks with ReLU activation.
Deep networks can learn functions approximated by shallow networks, but not all functions.
problem The learnability of functions by deep neural networks and the approximation capacity of simpler classes.
method Study the connection between learnability and approximation capacity of functions by deep neural networks and simpler classes.
result A necessary condition for a function to be learnable by deep neural networks is to be approximable by shallow networks.
Deep networks can approximate high-dimensional distributions from low-dimensional ones.
problem Approximating high-dimensional distributions from low-dimensional ones.
method Proved neural networks can transform low-dimensional distributions to high-dimensional ones with arbitrary closeness measured by Wasserstein distances and maximum mean discrepancy.
result Upper bounds of the approximation error are obtained in terms of the width and depth of neural network.
(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training. Learning domain-invariant features helps to achieve this goal, whereas it underpins unlabeled samples drawn from a single or multiple explicit target domains …
Proposes a new method to improve target annotation in ATR.
problem Challenges in annotating automatic target recognition due to lack of labeled data.
method Hybrid contrastive learning and cycle-consistency-based transductive transfer learning (C3TTL) framework.
result Significantly lower Fréchet Inception Distance (FID) score and improved performance in annotating civilian and military vehicles, as well as ship targets.
The paper tackles adaptive targeting in networks with interference effects.
problem Adaptive targeting under network interference in a bandit setting.
method Linear model in a sparse regime, analyzing different levels of knowledge of the interference structure.
result Unified view of how knowledge of the interference structure affects online learning efficiency.
Enhances neural network robustness with Mixup and TLAT.
problem Neural networks are sensitive to various perturbations and adversarial examples.
method Combines Mixup augmentation with Targeted Labeling Adversarial Training (TLAT).
result M-TLAT increases robustness against 19 corruptions and 5 adversarial attacks without reducing clean sample accuracy.
This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing met…
TILT improves target domain performance by penalizing an auxiliary component on unlabeled target inputs.
problem Improving performance on target domain under covariate shift.
method TILT uses a novel objective function to decompose the source predictor and penalize an auxiliary component on unlabeled target inputs.
result TILT improves target domain performance over source-only training and other baselines.
New method improves conditional covariance estimation using targeted groups of assets.
problem Improving conditional covariance estimation in financial time series.
method Introduces targeting in BEKK and DCC models for financial time series analysis.
result Encouraging results from empirical case study, especially with fewer assets.
Paper proposes methods to reduce financial contagion by targeted cash injections.
problem Financial contagion through interconnected networks.
method Dynamic model of payments with external control term for corrective cash injections.
result Targeted cash injections can significantly reduce default propagation.
Transfer learning is a very important tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet, discrepancies between the underlying distributions of the source and target data are c…
Deep neural networks improve free energy calculations for peptide conformations.
problem Challenges in developing suitable mappings for free energy perturbation.
method Adapted machine learning approach to train deep neural networks for mapping between Boltzmann distributions.
result Accurate free energy differences calculated between thermodynamic states with spring centers separated by 1 Å and sometimes 2 Å.
The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms and provide theoretical analysis on their conver…
Deep Neural Networks have been found vulnerable re-cently. A kind of well-designed inputs, which called adver-sarial examples, can lead the networks to make incorrectpredictions. Depending on the different scenarios, goalsand capabilities, the difficulties of the attacks are different.For example, a targeted attack is …
Deep neural networks can generate any 2D distribution with high accuracy.
problem Generating accurate high-dimensional distributions from random noise.
method A deep neural network with a space-filling property of sawtooth functions.
result The network can approximate any 2D Lipschitz-continuous distribution arbitrarily closely.
Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data augmentation has been gradually replaced by automatically learned augmentation policy. Through finding the best policy in well-designed search space of data augmentation, AutoAugment…
Policy-gradient method controls multiple non-cohesive targets.
problem Controlling multiple non-cohesive targets in a decentralized manner.
method Proximal Policy Optimization for target selection and driving.
result Effective control of non-cohesive targets without prior dynamics knowledge.
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adap…
GRAC improves reinforcement learning by self-guiding and self-regularizing.
problem Learning divergence and slow updates in reinforcement learning algorithms.
method Self-regularized TD-learning and self-guided policy improvement.
result Achieved or outperformed state-of-the-art results on OpenAI gym tasks.
Method transfers knowledge without label overlap, source data, or target architecture consistency.
problem Difficulties in transfer learning due to label mismatch, restricted source data, and specialized target architectures.
method Uses deep generative models in two stages: pseudo pre-training and pseudo semi-supervised learning.
result Outperforms scratch training and knowledge distillation methods.