We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on…
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “dynamic baseline”
An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and analyze a new model-based approach to compute a safe policy when we have access …
Prediction of cancer dynamics under treatment using Bayesian neural networks: A simulated studyq-bio.QM
Bayesian neural networks improve cancer dynamics prediction.
problem Predicting cancer dynamics under treatment due to heterogeneity and sparse data.
method Hierarchical Bayesian model using baseline covariates and Bayesian neural networks for nonlinear interactions.
result Bayesian neural networks outperform linear models in predicting cancer dynamics with interactions.
Bayesian method detects neuron spike activities from noisy fluorescence data.
problem Detecting neuron spike activities from noisy fluorescence data.
method Random finite set (RFS) based Bayesian approach.
result Gains 12% extra detection accuracy compared to MLSpike method.
Predictive Sparse Manifold Transform learns dynamic video sequences.
problem Learning and predicting natural dynamics in video sequences.
method Two-layer framework: sparse coding and manifold learning.
result PSMT with dynamic embedding space outperforms static baselines in future frame prediction.
Meta-learning improves drone trajectory design for dynamic wireless networks.
problem Designing optimal trajectories for energy-constrained drones in dynamic network environments.
method Proposes a meta-learning algorithm to adaptively tune a reinforcement learning solution for trajectory design.
result Meta-tuned RL yields faster convergence and improved communication performance compared to baseline algorithms.
Safe RL in linear systems achieves -regret.
problem Efficiently learning in safety-constrained online reinforcement learning.
method Study of linear quadratic regulator with safety constraints.
result First safe algorithm with -regret.
Enhances survival analysis by separating population behavior from individual dynamics.
problem Improving the training and inference of survival analysis models for sparsely occurring events.
method Decouples survival analysis into an aggregated baseline hazard and independent survival scores.
result Achieves competitive performance and robust results without fine-tuning.
DIVA clusters dynamic data without needing cluster count, outperforming baselines.
problem Clustering complex, dynamic data without prior knowledge of cluster count.
method Nonparametric Dirichlet Process Mixtures with memoized online variational inference.
result DIVA outperforms state-of-the-art in classifying complex data with changing features.
WiGS improves active learning for regression by dynamically selecting informative samples.
problem Reducing labeling costs in regression tasks.
method Formulated as a reinforcement learning problem, WiGS adapts the exploration-investigation balance.
result WiGS outperforms static methods in accuracy and labeling efficiency, especially in irregular data density.
ABC method improves subseasonal weather forecasting by 60-90%.
problem Improving subseasonal temperature and precipitation forecasting accuracy.
method Combines dynamical forecasts with machine learning-based bias correction.
result Significant improvement in temperature and precipitation forecasting skills.
Dynamic sparseness reduces neural network computation by selectively omitting parts of computations.
problem Reducing the computational and memory footprint of neural networks.
method Combining dynamic sparseness with block-wise matrix-vector multiplications to selectively omit parts of computations.
result The proposed method outperforms static sparseness and achieves similar perplexities at half the computational cost.
Paper introduces new tasks and a model class that can solve them, using mixtures of stochastic vector fields.
problem Neural ODEs cannot solve fundamental tasks even with high-capacity vector fields.
method Proposes mixtures of stochastic vector fields and dynamic vector field selection.
result Demonstrates that the proposed model class can capture natural dynamics of human behavior.
A lightweight network and NAS method improve ASC tasks.
problem Heavy computational burden in acoustic scene classification.
method Inspired by MobileNetV2, unidirectional convolutions; dynamic NAS with evolutionary algorithm.
result 90.3% F1-score on DCASE2018 task 5, 25% fewer FLOPs.
Enhances network intrusion detection in noisy data.
problem Robustness against contaminated and noisy data inputs in network intrusion detection.
method Probabilistic Temporal Graph Network Support Vector Data Description (TGN-SVDD) model.
result Significant improvements in detection performance with synthetic noise.
We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any human intervention. Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each …
This paper compares eight DRL algorithms for dynamic hedging.
problem Optimal dynamic hedging strategies using Deep Reinforcement Learning.
method Eight DRL algorithms (MCPG, PPO, DQL, DDPG) compared using a GJR-GARCH(1,1) simulated dataset.
result MCPG and PPO outperform the Black-Scholes delta hedge baseline.
The paper reveals that baselines significantly impact RL algorithms' convergence.
problem Understanding the true impact of baselines on policy optimization.
method Theoretical analysis of bandit and RL problems, focusing on natural policy gradient and EXP3.
result Baselines can determine algorithm convergence, contradicting traditional optimization theory.
How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embe…
TGN outperforms static GNNs in detecting financial fraud.
problem Anomaly detection in dynamic financial networks.
method Temporal Graph Networks (TGN) for capturing edge dynamics.
result TGN significantly outperforms static GNNs in AUC metrics.
Prototype controls stochastic drug resistance in cells.
problem Emergence of drug-resistant cells from random mutations.
method Deep reinforcement learning for adaptive drug dosing.
result 100% success rate in suppressing cell proliferation.
This work identifies eigenvalues of unknown linear dynamics without full system identification.
problem Identifying parameters of a linear dynamical system is challenging.
method Developed a computationally efficient algorithm to estimate eigenvalues of the state-transition matrix.
result The algorithm can efficiently cluster multi-dimensional time series with temporal offsets and varying lengths.
We study the performance of stochastically trained deep neural networks (DNNs) whose synaptic weights are implemented using emerging memristive devices that exhibit limited dynamic range, resolution, and variability in their programming characteristics. We show that a key device parameter to optimize the learning effic…
Robots learn object dynamics from visuals using GNNs and relational biases.
problem Challenging for robots to reason like humans about physical interactions.
method Graph Neural Networks (GNNs) with relational inductive bias.
result Auto-Predictor outperforms GN-based models and auto-encoder baseline.
The paper analyzes variance reduction in stochastic gradient Langevin dynamics.
problem Reducing the variance of stochastic gradient estimators in Langevin dynamics.
method Central limit theorem and Poisson equation analysis for variance characterization.
result Anti-symmetric perturbations can reduce the variance of non-reversible Langevin dynamics.
We propose a simple discrete time semi-supervised graph embedding approach to link prediction in dynamic networks. The learned embedding reflects information from both the temporal and cross-sectional network structures, which is performed by defining the loss function as a weighted sum of the supervised loss from past…
This work proposes a meta-learning approach for better adaptation of source code models.
problem Adapting source code models to unseen local contexts.
method Formulated as a meta-learning problem, selecting targeted information for adaptation.
result Improved performance in code auto-completion tasks, especially for identifiers and literals.
Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in static settings and an unsupervised manner. However, entities in real-world are often involved in many different relationships, consequently enti…
Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learningcs.CV
CBDA improves active learning for semantic segmentation, especially with imbalanced classes.
problem Class imbalance degrades performance in domain adaptive active learning.
method Class Balanced Dynamic Acquisition (CBDA) selects more balanced labels for active learning.
result CBDA increases minority class performance and outperforms baselines by 0.6-2.4 mIoU.
Prediction of the progression of subcortical brain structures in Alzheimer's disease from baselinecs.CV
We propose a method to predict the subject-specific longitudinal progression of brain structures extracted from baseline MRI, and evaluate its performance on Alzheimer's disease data. The disease progression is modeled as a trajectory on a group of diffeomorphisms in the context of large deformation diffeomorphic metri…
Introduces alternators for modeling sequences, outperforming baselines.
problem Modeling complex sequential data with stability and efficiency.
method Two neural networks (OTN and FTN) alternate between outputting samples in observation and feature spaces, learned via cross-entropy criterion.
result Alternators outperform strong baselines in various domains (Lorenz equations, Neuroscience, Climate Science).
Node-perturbation learning is a type of statistical gradient descent algorithm that can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. It estimates the gradient of an objective function by using the change in the object function in response to the per…
Modeling high-frequency order book data with Hawkes-Markovian process.
problem Capturing the dynamics of high-frequency order book events.
method Hawkes process with Markovian baseline intensities, LASSO regularization, and Akaike Information Criteria.
result Effective modeling of order book dynamics with reduced parameter redundancy.
New RL method improves robustness across various conditions.
problem Training robust RL agents for diverse environments.
method Adversarial training with Langevin Dynamics.
result Consistently outperforms existing RL algorithms in generalization.
SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.
problem Unbounded metric movement costs in bandit online convex optimization.
method SCaLE algorithm for high-dimensional dynamic quadratic hitting costs and -norm switching costs, with spectral regret analysis.
result First algorithm achieving sub-linear dynamic regret without hitting cost knowledge.
DySAT learns dynamic graph node representations capturing structural and temporal patterns.
problem Learning latent representations of nodes in dynamic graphs.
method Dynamic Self-Attention Network (DySAT) that combines self-attention layers for structural and temporal dimensions.
result DySAT outperforms state-of-the-art baselines in link prediction on dynamic graphs.
Soft geometric bias improves physical dynamics predictions.
problem Learning physical dynamics with exact group equivariance can degrade performance.
method Object-centric world models using geometric algebra neural networks.
result Soft geometric inductive bias leads to better physical fidelity predictions.
Bayesian Federated Learning improves model reliability in dynamic environments.
problem Uncertainty quantification and robust adaptation in distributed learning.
method Proposes a continual BFL framework using SGLD for sequential updates and continual learning challenges.
result Continual Bayesian updates preserve knowledge and adapt to evolving data.
DBNs predict cryptocurrency price directions by uncovering causal relationships.
problem Predicting cryptocurrency price movements due to volatility and external factors.
method Dynamic Bayesian Networks (DBN) approach to identify causal relationships among features.
result DBN significantly outperforms baseline models in predicting cryptocurrency prices.
Paper develops a new model for dynamic graph representation learning.
problem Learning over dynamic graphs with changing topology and node attributes.
method Hierarchical variational model with latent random variables and semi-implicit variational inference.
result SI-VGRNN and VGRNN outperform existing methods in dynamic link prediction.
Dynamical analysis of financial stocks network: improving forecasting using network propertiesq-fin.ST
Network analysis improves stock return forecasting.
problem Improving stock return forecasting using network properties.
method Network analysis of stock return correlations, using individual and global properties of stocks.
result 50% improvement in R2 score for long-term stock returns forecasting, 3% for short-term.
AI-driven tax policies improve economic equality and productivity.
problem Lack of appropriate economic data and limited opportunity to experiment.
method Two-level deep reinforcement learning approach to learn dynamic tax policies from observational data.
result AI-driven tax policies improve the trade-off between equality and productivity by 16%.
Paper introduces Tensor Gauge Flow Models for better data encoding.
problem Lack of expressive flow dynamics in existing Generative Flow Models.
method Incorporates higher-order Tensor Gauge Fields into the Flow Equation.
result Tensor Gauge Flow Models achieve improved generative performance.
Global Stock Market Volatility Forecasting Incorporating Dynamic Graphs and All Trading Daysq-fin.GN
Model forecasts global stock market volatility using dynamic graphs and all trading days.
problem Enhance forecasting accuracy and practical utility in global stock market volatility.
method Spatial-temporal graph neural network architecture to capture volatility spillover effect.
result Forecasting performance surpasses baseline models in all scenarios.
Deep learning observables in computational fluid dynamicsphysics.comp-ph
Deep learning predicts fluid dynamics parameters from few samples.
problem Challenging computational fluid dynamics problems requiring many expensive PDE solutions.
method Deep artificial neural networks trained on a few samples to predict input parameters to observable.
result Robust and efficient neural network approximations of parameters to observable map, with low prediction errors and computational savings.
Learning nonlinear dynamics from diffusion data is a challenging problem since the individuals observed may be different at different time points, generally following an aggregate behaviour. Existing work cannot handle the tasks well since they model such dynamics either directly on observations or enforce the availabi…
GFM models neural network training as a dynamical system to forecast final weights.
problem Computational intensity and inefficiency in training deep neural networks.
method Gradient Flow Matching (GFM) treats training as a dynamical system with learned vector fields.
result GFM achieves forecasting accuracy competitive with Transformer-based models and significantly outperforms classical baselines.
HySRL improves RL sample efficiency with shifted-dynamics data.
problem Leveraging historical data with shifted dynamics to improve sample efficiency in RL.
method HySRL, a hybrid transfer RL algorithm that uses prior information on dynamics shift to achieve better sample complexity.
result HySRL achieves problem-dependent sample complexity and outperforms pure online RL.