Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid l…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Soft Value Function”
Boosts Q-learning by using value function bounds.
problem Efficiently solving new tasks using past experience.
method Derives double-sided bounds on optimal value function and uses them to update Q-function.
result Boosted training performance through alternative Q-function update method.
New method improves stability of soft FQI for offline RL.
problem Stability issues in soft FQI under function approximation.
method Stationary reweighting to align operator norms.
result Local linear convergence proved under certain conditions.
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcs.LG
New method optimizes diffusion models without fine-tuning, integrating soft value functions.
problem Optimizing natural design spaces of images, molecules, DNA, RNA, and protein sequences.
method Iterative sampling method integrating soft value functions into diffusion model inference.
result Directly utilizes non-differentiable features/reward feedback, applies to discrete diffusion models.
New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.
problem Offline RL with limited exploration and assumptions about data coverage and Q-function realizability.
method Proposes minimax learning algorithms to estimate soft or vanilla Q-functions with -convergence guarantees.
result PAC guarantees for offline RL under partial coverage and realizability conditions.
Developed a new thresholding method that connects soft and hard thresholding.
problem Connecting soft and hard thresholding methods in data analysis.
method Scaled soft thresholding method with empirical scaling values.
result Found two sources of over-fitting in the scaled soft thresholding method.
New method combines value function decomposition and policy gradients for cooperative multi-agent reinforcement learning.
problem Challenges in cooperative multi-agent reinforcement learning, especially credit assignment and large action spaces.
method Decomposed Soft Actor-Critic (mSAC) method with Q network architecture, discrete probabilistic policy, and counterfactual advantage function.
result Significantly outperforms policy-based approach COMA and achieves competitive results with SOTA value-based approach Qmix.
We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically so…
We present a fully nonparametric method to estimate the value function, via simulation, in the context of expected infinite-horizon discounted rewards for Markov chains. Estimating such value functions plays an important role in approximate dynamic programming and applied probability in general. We incorporate "soft in…
Band-limited SAC improves learning efficiency and stability in simulated environments.
problem Improving sample efficiency and stability in SAC algorithms.
method Artificially bandlimiting the target critic's spatial resolution using a convolutional filter.
result Bandlimited SAC outperforms classic twin-critic SAC in various Gym environments and is more stable.
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge i…
Generative AI connects to Schrödinger bridge problems with soft constraints for stability.
problem Stability issues in generative AI due to hard terminal constraints.
method Soft-constrained Schrödinger bridge formulation and convergence analysis.
result Existence and convergence of optimal solutions as penalty grows.
Introduces Soft-SVM for binary classification bridging logistic and SVM.
problem Data separability issues in binary classification.
method Soft-SVM regression using convex relaxation of hinge loss with softness and class-separation parameters.
result Soft-SVM performs well in classification and prediction errors.
Nonlinearity is crucial to the performance of a deep (neural) network (DN). To date there has been little progress understanding the menagerie of available nonlinearities, but recently progress has been made on understanding the rôle played by piecewise affine and convex nonlinearities like the ReLU and absolute value …
Unified approach optimizes neural network training for various metrics.
problem Training and evaluation of neural network binary classifiers often use different metrics.
method Combines differentiable approximation and probabilistic soft sets.
result Effective in optimizing for metrics like F1-Score across various domains.
The problem of estimating a high-dimensional sparse vector from an observation in i.i.d. Gaussian noise is considered. The performance is measured using squared-error loss. An empirical Bayes shrinkage estimator, derived using a Bernoulli-Gaussian prior, is analyzed and compared with the…
Autoencoder Treescs.LG
We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall output is the average of all leaves weighted by the gating values on their path. …
Gaussian Process Classification with Privileged Information by Soft-to-Hard Labeling Transferstat.ML
Learning using privileged information is an attractive problem setting that helps many learning scenarios in the real world. A state-of-the-art method of Gaussian process classification (GPC) with privileged information is GPC+, which incorporates privileged information into a noise term of the likelihood. A drawback o…
Paper proposes a new loss function for conditional models using soft targets.
problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.
Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the action-values, with the addition of entropy regularization for soft variants. In th…
This work connects IRL methods from ML and economics.
problem Solving the inverse reinforcement learning problem.
method Shows connections and differences between various IRL methods.
result Identifies key computational and algorithmic differences.
Short note on soft-max and policy gradients in bandit problems using Lyapunov functions.
problem Analyzing soft-max and policy gradient methods in bandit problems.
method Lyapunov function argument for soft-max and differential equations for policy gradient algorithms.
result Regret bounds for soft-max and a different policy gradient algorithm in bandit problems.
Improved KNN data valuation method with reduced computation time.
problem Efficiently valuing individual data points in KNN models.
method Proposed a new utility function and derived its calculation for KNN classifiers/regressors, achieving similar time complexity as the original method.
result Soft-label KNN-SV outperforms the original method in mislabeled data detection.
A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.
problem Stabilizing model-free off-policy deep reinforcement learning with soft divergence.
method Representing past experiences as a QGraph, selecting a subgraph with favorable structure, and using lower bounds for temporal difference learning.
result QG-DDPG method is less prone to soft divergence and more robust to hyperparameters.
Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep learning, the autoencoder embraces a wide spectrum of applications, yet it suffers fro…
Soft-margin classification of object manifoldscond-mat.dis-nn
Theory for soft-margin classifiers on object manifolds.
problem Classifying object manifolds with variability.
method Mean-field theory of soft-margin classifiers applied to object manifolds.
result Prediction of classification errors and their dependence on regularization.
We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero probability for only a small number of actions. This addresses the main drawback of the …
SoftCLT improves time series representation learning by soft contrastive loss.
problem Ignoring inherent correlations in time series leads to poor representation quality.
method SoftCLT introduces instance-wise and temporal contrastive loss with soft assignments.
result SoftCLT consistently improves various downstream tasks in time series learning.
New framework improves interpretability of trainable prompts.
problem Improving task-specific LLM performance with soft prompts remains a black-box method.
method Developed a theoretical framework for evaluating interpretability of trainable prompts, inspired new objective functions.
result Found a fundamental trade-off between interpretability and task performance in trainable prompts.
Data-Driven Estimation of the False Positive Rate of the Bayes Binary Classifier via Soft Labelscs.LG
Paper estimates FPR of Bayes classifier using soft labels.
problem Determining optimal classifier performance.
method Uses soft labels and denoising technique.
result Consistent and unbiased FPR estimator developed.
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
A new type of distributional regression tree uses soft split rules for better predictive performance.
problem Estimating complete conditional distributions in regression.
method Distributional adaptive soft regression trees using multivariate soft split rules.
result The method outperforms various benchmark methods, especially in complex non-linear interactions.
Soft-constrained PINN solves ODEs with minimal data, improving efficiency and robustness.
problem Sparse and noisy data in experiments and simulations.
method Soft-constrained Physics-informed Neural Network (PINN) with minimal labeled data.
result Soft-constrained PINN reduces need for labeled data and achieves strong generalization.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft--function, solve the source and target system of equations jointly.
result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
Active learning improves soft sensor development by suggesting informative labels.
problem Expensive labeling of process variables in industrial settings.
method Adapted active learning strategies for online data streams and used semi-supervised autoencoders.
result Improved predictive performance of soft sensors using active learning and autoencoders.
In Domain Adaptation (DA), the category-relevant losses usually occupy a dominant position, while they are usually built with hard or soft labels in existing models. We observed that hard labels are overconfident due to hard samples existed, and soft labels are ambiguous as too many small noisy probabilities involved, …
The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be…
We use SMC with twist functions to improve probabilistic inference in LLMs.
problem Improving probabilistic inference in large language models.
method We use Sequential Monte Carlo with learned twist functions to estimate expected future values and focus inference on promising sequences.
result Twisted SMC improves the accuracy of language model inference and evaluation.
Paper tackles DOCTR-L with SciPhy RL, solving neural PDEs from data.
problem High-dimensional optimal control with stochastic policies.
method Soft HJB equation, Neural PDEs, Physics-Informed Neural Networks.
result Reduces DOCTR-L to solving neural PDEs from data.
Five simple soft sensor methodologies with two update conditions were compared on two experimentally-obtained datasets and one simulated dataset. The soft sensors investigated were moving window partial least squares regression (and a recursive variant), moving window random forest regression, the mean moving window of…
Study improves S&P 500 volatility forecasting through regime-switching methods.
problem Accurate prediction of S&P 500 volatility for risk management and investment.
method Regime-switching methods including soft Markov switching, spectral clustering, and coefficient-based clustering.
result Coefficient-based clustering algorithm outperformed other models during all time periods.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
problem Training neural networks to mimic the complex interactions of brain neurons.
method Developed a network-in-network architecture with two-input activation functions, optimized hyperparameters, and compared to conventional ReLU networks.
result Two-input activation functions can learn soft XOR functions, improving network performance and robustness.
HyperFair integrates fairness in recommender systems using probabilistic soft logic.
problem Ensuring fairness in recommender systems across diverse domains.
method Soft fairness constraints integrated as regularization in a joint inference objective function.
result HyperFair improves fairness of predictions from black-box models and hybrid systems.
In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with associated fixed point we call the `knowledge values'. These K-values compress both the …
LC-SAC tackles non-stationary dynamics in reinforcement learning.
problem Degradation of deep RL methods in non-stationary environments.
method LC-SAC uses latent context encoders and contrastive loss for dynamic information capture.
result LC-SAC outperforms SAC on environments with drastic dynamics changes.
It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. The methods based on reinforcement learning, such as inverse reinforcement l…
InfoPrompt improves soft prompt tuning by maximizing mutual information, leading to better performance.
problem High sensitivity of prompt tuning to initial conditions and insufficient task-relevant information.
method Develops an information-theoretic framework to maximize mutual information between prompts and model parameters, using novel loss functions.
result InfoPrompt accelerates convergence and outperforms traditional methods.
In this work, we introduce a deep learning-based polar code construction algorithm. The core idea is to represent the information/frozen bit indices of a polar code as a binary vector which can be interpreted as trainable weights of a neural network (NN). For this, we demonstrate how this binary vector can be relaxed t…