This work improves reinforcement learning with sparse rewards by following diverse past trajectories.
problem Challenges in reinforcement learning with sparse rewards and myopic behavior.
method Proposes a trajectory-conditioned policy to learn from a memory buffer of diverse past trajectories.
result Significantly outperforms existing methods on complex tasks with local optima.
MAPO uses a memory buffer to improve policy optimization in structured prediction tasks.
problem Improving sample efficiency and robustness in policy optimization for structured prediction tasks.
method Memory Augmented Policy Optimization (MAPO) uses a memory buffer to reduce policy gradient variance.
result MAPO achieves state-of-the-art results in program synthesis and semantic parsing tasks.
Paper predicts future vehicle trajectories for safer AVs.
problem Improving accuracy of long-term vehicle trajectory prediction for autonomous vehicles.
method Dual LSTM network for automatic learning of driver behaviors and future trajectory prediction.
result The method achieves lower RMSE for longitudinal and lateral predictions compared to state-of-the-art methods.
Novel method learns memory kernels in Langevin equations.
problem Estimating memory kernels in Langevin equations.
method Regularized Prony method for correlation functions, followed by regression over Sobolev norm-based loss function with RKHS regularization.
result Method outperforms other regression estimators in exponentially weighted L^2 space.
The study analyzes prediction errors in systems with memory kernels, providing bounds and stability results.
problem Prediction errors in stochastic dynamical systems with memory kernels.
method Analysis of generalized Langevin equations (GLEs) with Volterra equations, integrating synchronized noise coupling and weighted norms.
result Prediction discrepancies decay at a rate determined by the memory kernel's decay, quantitatively bounded by kernel estimation errors.
JKO-iFlow uses neural ODEs to improve generative models with reduced memory and training complexity.
problem Efficiently training deep generative models in high dimensions with reduced memory and training complexity.
method JKO scheme inspired neural ODE flow network with adaptive time reparameterization.
result JKO-iFlow achieves competitive performance compared to existing models at reduced computational and memory cost.
Deep learning detects inaccurate smart meters for resource savings.
problem Detecting and replacing inaccurate smart meters to save resources.
method Developed a deep-learning method using LSTM and CNN to predict electricity usage trajectories.
result High accuracy in detecting inaccurate meters for practical usage.
TRAKNN detects rare atmospheric trajectories efficiently.
problem Detecting rare atmospheric anomalies over long periods.
method Unsupervised, recurrence-based kNN algorithm.
result Rare trajectories correspond to physical anomalies.
Revisiting Trade-sign Long-memory and Square-root Law price impact
problem Revisiting the Lillo-Mike-Farmer (LMF) theory and the square-root law (SQRL) of meta-order impact
method Using a coupled discrete reaction-diffusion formulation
result Long-memory of trade signs and square-root law of meta-order impact
Intelligence emerges from stabilizing invariant cycles in memory.
problem Understanding the nature of intelligence and its emergence.
method Structural-dynamical account rooted in a topological closure law: \(\partial^2=0\).
result Memory-amortized inference (MAI) mechanism that implements SbS \(
ightarrow\) CCUP.
Combines model-free Q-ensembles and model-based approaches for improved exploration.
problem Improving exploration strategies in reinforcement learning.
method Integrates model-free Q-ensembles and model-based trajectory memory approaches.
result Model-based trajectory memory combined with Q-ensembles outperforms Q-ensembles alone.
Study adds memory effect to Solow-Swan model for more accurate economic growth modeling.
problem Inaccuracies in classical Solow-Swan model in capturing long-term dynamics.
method Introduced fractional calculus with Caputo derivative into Solow-Swan framework.
result Fractional-order model shows significant impact on capital accumulation and stability.
SDA method reduces memory and time for assimilating noisy geophysical data.
problem Challenges in identifying state trajectories of high-dimensional geophysical systems.
method Score-based data assimilation with modified score network architecture.
result Promising results for a two-layer quasi-geostrophic model.
New CTRW model with memory explains long-term return autocorrelation.
problem Explaining long-term autocorrelation in financial returns.
method Proposed a Directed Continuous-Time Random Walk (CTRW) model with memory, considering only positive jumps and dependence on previous jumps.
result Bid-ask bounce explains only a small fraction of the long-term autocorrelation in financial returns.
MAYA learns bee foraging decisions with limited memory.
problem Reproducing and predicting bees' foraging decisions with limited memory.
method Sequential imitation learning model based on multi-armed bandits, considering a temporal window τ of 7 trials.
result MAYA outperforms imitation baselines and classical models, providing interpretability and realistic trajectories.
This research predicts vehicle movements by analyzing their intentions relative to road lanes.
problem Accurately forecasting vehicles' future movements for safe autonomous driving.
method LSTM networks with attention mechanisms applied to spatio-temporal graphs of road lanes.
result The model outperforms other state-of-the-art models in several metrics.
Paper presents a new Wi-Fi RSS and geomagnetic field database for indoor localization and trajectory estimation.
problem Indoor localization and trajectory estimation challenges.
method Convolutional neural network (CNN) for RSS data and LSTM network for geomagnetic field intensity.
result CNN and LSTM networks show feasibility for localization and trajectory estimation.
New model captures long-term memory effects in epidemic dynamics.
problem Identifying memory effects in disease progression and recovery.
method Physics-informed neural networks (PINN) with fractional SEIRD model.
result Fractional memory order α improves predictive performance over classical models. Proposes a plastic neural memory model for better anomaly detection.
problem Static attention mechanisms limit NMNs in anomaly detection.
method Introduces dynamic connection weights for improved knowledge retrieval.
result Outperforms state-of-the-art in three medical anomaly detection tasks.
A new memory-efficient Adam variant reduces second moments when feasible.
problem Memory constraints in training machine learning models.
method Signal-to-Noise Ratio (SNR) analysis to identify dimensions where second moments can be replaced by means.
result Memory-efficient Adam variant (SlimAdam) matches performance and stability of Adam while saving up to 98% of second moments.
This paper introduces a hierarchical associative memory model with multiple layers.
problem Limitations of traditional associative memory models with only one hidden layer.
method Develops a fully recurrent model with arbitrary layers, including locally connected ones, and a corresponding energy function.
result The model can dynamically assemble memories using weights from lower layers and higher layers' rules.
Deep neural nets predict aircraft flight paths from weather data.
problem Accurate prediction of aircraft trajectories for aviation efficiency.
method Deep generative convolutional recurrent neural network with tree-based matching.
result Model accurately predicts aircraft flight paths from weather data.
Transformers can store facts efficiently using associative memories.
problem Understanding how transformers store and recall factual information.
method Proved linear scaling of storage capacities for linear and MLP associative memories, introduced a synthetic task, and analyzed gradient flow.
result Shallow transformers can achieve near optimal storage capacity for factual recall tasks using associative memories.
HiPPO framework optimizes memory compression for sequential data.
problem Incremental representation of cumulative history in sequential data.
method Optimal polynomial projections for online function approximation.
result HiPPO-LegS achieves state-of-the-art accuracy on MNIST.
New analysis shows FM learns underlying dynamical structure, not just trajectory replay.
problem Understanding whether flow matching models learn transferable dynamical structure or merely replay trajectories.
method Derived velocity field implied by FM objective, characterized as a continuous-time dynamical system.
result FM models can be seen as parametric surrogates of nonparametric solutions, providing strong probabilistic forecasts.
Paper uses RNNs for more accurate indoor WiFi localization.
problem Accurate indoor WiFi localization using RSSI measurements.
method Proposes recurrent neural networks (RNNs) for trajectory positioning of RSSI data.
result Achieves an average localization error of 0.75 m with 80% under 1 m, outperforming conventional algorithms.
StreaMRAK improves KRR for streaming data.
problem Streaming data with memory constraints.
method Divides problem into levels of resolution, sub-sampling.
result Efficiently integrates new samples, reduces memory and complexity.
Personalized predictive medicine necessitates the modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, an end-to-end deep dynamic neural network t…
CEM-GD combines CEM and gradient descent for efficient model-based RL.
problem Efficient planning in continuous control settings with large prediction horizons.
method Combines CEM for exploration and gradient descent for exploitation.
result Achieves better performance with fewer samples and less computation time.
CDP improves RL performance and sample-efficiency by prioritizing rare goal states.
problem Learning from imbalanced data in RL.
method Curiosity-Driven Prioritization (CDP) framework.
result CDP improves both performance and sample-efficiency of RL agents.
Algorithm learns linear systems from partial observations with near-optimal rate.
problem Identifying linear dynamical systems from partial observations, especially those with long-term memory.
method Multi-scale low-rank approximation using SVD on Hankel matrices of increasing sizes, combined with Fourier domain concentration bounds.
result Near-optimal rate of $\widetilde O\left(\sqrt\frac{d}{T}
ight)$ in H2 error, with logarithmic dependence on memory length. Algorithm creates synthetic experiences to enhance Deep Reinforcement Learning.
problem Lack of synthetic experiences in classic Experience Replay.
method Bootstraps synthetic experiences to augment the replay memory.
result Synthetic experiences can improve learning speed and performance.
Accurate diagnosis of Alzheimer's Disease (AD) entails clinical evaluation of multiple cognition metrics and biomarkers. Metrics such as the Alzheimer's Disease Assessment Scale - Cognitive test (ADAS-cog) comprise multiple subscores that quantify different aspects of a patient's cognitive state such as learning, memor…
A new method predicts non-Markovian closure terms for complex systems.
problem Predicting the effect of unresolved variables on resolved dynamics in high-dimensional systems.
method Mamba-Assisted Closure (MAC) framework: sequence model trained to predict closure from resolved trajectory, coupled with reduced-order equations.
result Substantially outperforms existing methods in predictive accuracy and long-time stability.
Agents learn to outperform in trading by using past and current prices.
problem Optimal trading performance beyond theoretical limits.
method Two-agent Almgren-Chriss liquidation game, schedule-learning, DDQN architectures.
result Agents with access to past and current prices achieve supra-competitive outcomes.
DCRNN improves LSTM for chaotic dynamical system forecasting.
problem Modeling chaotic dynamical systems with recurrent neural networks.
method DCRNN incorporates learnable skip-connections and a Lyapunov stability regularization term.
result DCRNN outperforms LSTM in 100 out of 100 experiments, reducing mean squared error by 80.0%.
ERM uses energy-based selection to improve recursive reasoning.
problem Lack of principled inference mechanism in recursive models.
method Energy-guided Recursive Model (ERM) introduces Hopfield energies for trajectory selection.
result ERM achieves optimal solutions on various puzzles.
Develops methods to learn correlation potentials for time-dependent Kohn-Sham systems.
problem Learning the correlation potential for time-dependent Kohn-Sham systems.
method Optimizing a least-squares objective subject to the TDKS equation using adjoints.
result Learned correlation potential models match ground truth electron densities and can have memory.
LLM trading agents show risk feedback can improve alignment without fine-tuning.
problem Aligning LLM trading agents with financial risk.
method TradeArena testbed, risk reports, execution simulation, memory replay.
result Risk feedback can improve alignment without fine-tuning, but not universally.
Improved CEM for fast real-time planning in high-dimensional control tasks.
problem Sampling inefficiency of CEM in real-time planning.
method Novel additions to CEM including temporally-correlated actions and memory.
result 2.7-22x less samples and 1.2-10x performance increase.
condLSTM-Q predicts COVID-19 deaths at county level with quantile forecasts.
problem Predicting COVID-19 mortality at fine geographical scales.
method Conditional Long Short-Term Memory networks with quantile output.
result Fine-scale quantile predictions inform about death toll distribution.
Deep-IRT combines deep learning and IRT for explainable knowledge tracing.
problem Lack of explainability in deep learning-based knowledge tracing models.
method Synthesis of DKVMN and IRT models to estimate student and item parameters.
result Deep-IRT retains DKVMN performance while providing psychological interpretations.
Learning and memory in the brain are implemented by complex, time-varying changes in neural circuitry. The computational rules according to which synaptic weights change over time are the subject of much research, and are not precisely understood. Until recently, limitations in experimental methods have made it challen…
Researchers develop a generalised geometric Brownian motion for better asset pricing.
problem Irregularities in simple geometric Brownian motion for asset dynamics.
method Introduce a memory kernel to generalise GBM, derive moments and probability density functions.
result The performance of kernels in pricing options depends on option maturity and moneyness.
HS-FNO models non-Markovian PDEs by learning history and future states.
problem Non-Markovian dynamics where future states depend on past history.
method History-Space Fourier Neural Operator (HS-FNO) for delay and memory-driven PDEs.
result HS-FNO achieves lowest aggregate errors across various PDE families.
New method prevents deep learning models from forgetting past tasks.
problem Catastrophic forgetting in continual learning.
method Direction-constrained optimization (DCO) with autoencoders.
result Model performance is improved without forgetting past tasks.
Proposes LSTM algorithm for robust Alzheimer's disease progression modeling with missing data.
problem Challenges in modeling disease progression using incomplete longitudinal data.
method Utilizes Long Short-Term Memory (LSTM) networks for Alzheimer's disease progression modeling with a generalized training rule for handling missing data.
result Achieves significantly lower mean absolute error (MAE) than alternatives with p < 0.05.
SDSM extracts statistically significant sub-trajectories from large trajectory datasets.
problem Discerning moving patterns that are more characteristic of one group of trajectories than another.
method Statistically Discriminative Sub-trajectory Mining (SDSM) method using tree representation and permutation-based statistical inference.
result SDSM efficiently extracts statistically significant sub-trajectories from massive trajectory datasets.