Algorithm generates private continuous-time data for sensitive domains.
problem Private generation of continuous-time data for sensitive domains.
method Mean-field Langevin dynamics and noisy particle gradient descent.
result Strong privacy guarantees for one-time data contributions.
Paper analyzes CCT sensitivity in constrained power systems, offering insights into system stability and parameter changes.
problem Identifying preventive control measures to avoid large generation losses during disturbances.
method Derived first-order CCT sensitivity for generic constrained power systems using trajectory sensitivity computation.
result Sensitivity of CCT to system parameters, providing insights into feasibility and stability.
NDDV estimates data point value from a single stochastic trajectory.
problem Estimating marginal contributions of data points over stochastic training paths.
method Introduces Neural Dynamic Data Valuation (NDDV) using stochastic state and adjoint equations.
result NDDV provides a one-run, trajectory-conditioned estimator of data point value.
The study identifies conditions under which algorithmic stability explains generalization in interpolating learning systems.
problem Understanding when algorithmic stability explains generalization in interpolating learning systems.
method Modeling training as a function-space trajectory and measuring sensitivity to single-sample perturbations.
result There exist interpolating regimes with small risk where contractive sensitivity cannot hold, showing that stability is not a universal explanation.
Optimizes portfolios by identifying causal drivers of diversification.
problem Achieving efficient portfolio optimization based on asset and diversification dynamics.
method Commonality Principle, Reichenbach Common Cause Principle, conformal maps, Bayesian networks, correlation-based algorithms, neural networks, SDEs.
result Optimal portfolio diversification achieved through causal methodologies and sensitivity forecasting.
Enhances Random Forest for imbalanced functional data classification.
problem Challenges in classifying imbalanced functional data.
method Functional Random Forest with Adaptive Cost-Sensitive Splitting (FRF-ACS).
result Significantly improves minority class recall and predictive performance.
We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute. Our approach is based on an interrelated set of measures of expressivity, unified by the novel notion of trajectory length…
Proposes DGCN with trajectory sampling for data-efficient policy search in MBRL.
problem Improving data efficiency in model-based reinforcement learning.
method Combines trajectory sampling and DGCN for uncertainty propagation in probabilistic world models.
result Improves sample-efficiency over other uncertainty propagation methods and probabilistic models.
Adjoint SA speeds up bioprocess parameter learning.
problem Challenges in digital twin development for biomanufacturing.
method Adjoint sensitivity analysis on multi-scale enzymatic reaction networks.
result Resilient sensitivities reveal bioprocess regulatory mechanisms.
This paper introduces a method to incorporate risk sensitivity in RL using quadratic variation penalties.
problem Risk-sensitive reinforcement learning under entropy regularization.
method Equivalent martingale property and quadratic variation penalty for value process.
result The proposed method improves finite-sample performance in linear-quadratic control problems.
We study the effect of parameters uncertainties on a stochastic diffusion model, in particular the impact on the pricing of contingent claims, thanks to Dirichlet Forms methods. We apply recent techniques, developed by Bouleau, to hedging procedures in order to compute the sensitivities of SDE trajectories with respect…
We study the effect of parameter uncertainty on a stochastic diffusion model, in particular the impact on the pricing of contingent claims, using methods from the theory of Dirichlet forms. We apply these techniques to hedging procedures in order to compute the sensitivity of SDE trajectories with respect to parameter …
New method learns nonlinear systems from single finite trajectory samples.
problem Learning stabilizable nonlinear systems from single finite trajectory samples.
method Gradient-based algorithms with noise-sensitive uniform convergence guarantees.
result Efficient learning of general nonlinear systems with high accuracy and small sample complexity.
Differentially private policy evaluation improves reinforcement learning efficiency.
problem Sample inefficiency in reinforcement learning.
method Differentially private actor-critic model initialization.
result Improves sample efficiency in control problems.
Stable GFlowNets prevent loss spikes and mode collapse in training.
problem Unstable training of GFlowNets leading to loss spikes and mode collapse.
method Assessed sensitivity of GFlowNet objectives, derived loss-to-TV bounds, and proposed Stable GFlowNets.
result Stable GFlowNets improve training behavior and distributional fidelity.
ToolChain-CRC addresses the risk-control problem for retrieval-augmented and tool-using agents under drift.
problem Risk-control problem for retrieval-augmented and tool-using agents under drift.
method ToolChain-CRC uses conformal risk-control under exchangeable calibration runs.
result Trajectory-level risk control keeps accepted-trajectory risk below the target.
A new method learns policies from sub-optimal trajectories.
problem Reinforcement learning's brittleness and difficulty in tuning.
method Conditioning policies on the reward of sub-optimal trajectories.
result Effective policies can be learned without expert demonstrations.
A new method learns physical system sensitivity to improve policy learning without needing a full model.
problem Expensive policy learning without models and model bias.
method Learn sensitivity of trajectories to parameter perturbations.
result Feasibility demonstrated on a physical robot.
Captures data influence changes during training.
problem Traditional influence functions fail for modern training methods.
method Formalized trajectory-specific LOO influence, using data value embedding.
result Data influence varies by training stage, early and late stages have greater impact.
Fractured Sampling improves LLM reasoning efficiency by truncating CoT trajectories.
problem Efficiently scaling reasoning in large language models with limited tokens.
method Integrating truncated Chain-of-Thought (CoT) with Fractured Sampling across multiple dimensions.
result Fractured Sampling achieves superior accuracy-cost trade-offs compared to full CoT.
Framework for continuous-time network data representation learning.
problem Learning reliable representations of dynamic network interactions.
method Three-stage process: intensity estimation, projection learning, evolving node representation construction.
result Trajectories satisfy structural and temporal coherence, providing robust inference.
Study optimizes interbank lending and borrowing to reduce systemic risk.
problem Optimizing lending and borrowing in interbank markets to mitigate systemic risk.
method Risk-sensitive mean field games with common noise, convex analysis, Fokker-Planck equations, first hitting time method.
result Risk-averse behavior reduces individual and systemic bank risks.
VLBM learns MDP transitions from limited data, improving OPE performance.
problem Limited coverage of state and action space in offline trajectories.
method VLBM uses variational inference with RSA and branching architecture.
result VLBM outperforms existing OPE methods on deep OPE benchmark.
FCNv2 robustness tested under noise and random initial conditions.
problem Assessing AI weather forecasting model robustness to input noise.
method Two experiments with varying noise levels and random initial conditions.
result FCNv2 preserves hurricane features under low to moderate noise, but underestimates intensity and persistence.
C-kNN-LSH identifies similar patient histories for causal inference in longitudinal data.
problem Estimating causal effects from longitudinal trajectories with high-dimensional confounding.
method C-kNN-LSH uses locality-sensitive hashing to find clinical twins and estimate treatment effects.
result C-kNN-LSH outperforms existing methods in capturing recovery heterogeneity and estimating policy values.
Study differential privacy in multi-agent RL, achieving efficient and private learning.
problem Protecting sensitive data in multi-agent reinforcement learning.
method Extending DP definitions to two-player games, designing an efficient algorithm with privatized bonuses.
result Achieved trajectory-wise differential privacy in multi-agent RL, improving regret bounds.
DHLNN improves deep hedging for financial derivatives with faster convergence and better stability.
problem Challenges in computational inefficiency, sensitivity to noisy data, and optimization complexity in deep hedging methods.
method Integrates periodic fixed-gradient optimization and linearized training dynamics to stabilize and accelerate deep learning model training.
result Demonstrates faster convergence, improved stability, and superior hedging performance across diverse market scenarios.
This thesis tackles data imperfections in ML, proposing methods to prevent discrimination and spurious feature learning.
problem Data imperfections in ML training data, leading to deployment failures.
method Fair representation learning, spurious feature detection, and data augmentation for reinforcement learning.
result Methods to make ML models more robust to data imperfections.
New method learns chaotic dynamics from single noisy trajectory.
problem Chaos in complex systems is hard to model accurately with machine learning.
method Adversarial optimal transport objectives to learn summary statistics and emulator from single noisy data.
result Emulators trained with proposed objectives have significantly improved long-term statistical fidelity.
Stable neural flows ensure robustness and efficiency in deep learning.
problem Ensuring robustness and stability in deep learning models.
method Introducing a stable variant of neural ODEs with a neural network parametrizing an energy functional, solving as an optimal control problem with adjoint sensitivity analysis.
result The proposed model provides robustness against input perturbations and low computational burden.
GLMM trees identify subgroups with different growth patterns in longitudinal data.
problem Identifying subgroups with distinct growth trajectories in longitudinal studies.
method Extended GLMM trees for longitudinal data.
result Extended GLMM trees outperform other methods in accuracy and speed.
We study the problem of discriminative sub-trajectory mining. Given two groups of trajectories, the goal of this problem is to extract moving patterns in the form of sub-trajectories which are more similar to sub-trajectories of one group and less similar to those of the other. We propose a new method called Statistica…
QuantaAlpha uses evolutionary algorithms to mine financial alpha robustly across market distributions.
problem Challenges in alpha mining due to market noise and regime shifts.
method Evolutionary framework treating each mining run as a trajectory, mutation, crossover, targeted revision, and reuse of effective patterns.
result Consistent gains over strong baselines and prior systems, achieving high IC and ARR.
The paper provides Gaussian approximations for decentralized Federated Learning.
problem Lack of asymptotic statistical guarantees for local SGD in Federated Learning.
method Two generalized Gaussian approximation results for local SGD trajectories.
result Valid multiplier bootstrap procedures and Gaussian bootstrap-based tests for detecting adversarial attacks.
Paper uses deep imitation learning to predict aircraft trajectories accurately.
problem Inefficient and costly Air Traffic Management system limits predictability.
method Generative Adversarial Imitation Learning framework with trajectory clustering and classification.
result Accurate predictions for entire trajectory stages, pre- and tactical.
Paper infers human mobility from sparse trajectories.
problem Modeling and inferring human mobility from sparse trajectory data.
method Proposes a single trajectory inference algorithm and a deep learning architecture for multiple trajectories.
result Deep learning model achieves 2x overall accuracy improvement on sparse trajectories.
Pattern ensembling fills in missing or inaccurate trajectory data.
problem Incompleteness, missing information, and inaccuracies in geolocation data.
method Probabilistically ensemble similar trajectory patterns from the vicinity.
result Reconstructs missing or unreliable trajectory segments effectively.
Study shows magnetic trajectories in Berger spheres are homogeneous.
problem Homogeneity of contact magnetic trajectories in Berger spheres.
method Proved every contact magnetic trajectory is a product of a homogeneous geodesic and a charged Reeb flow.
result Contact magnetic trajectories in Berger spheres are homogeneous.
Improved trajectory prediction for team sports using sparse outputs.
problem Challenging to train deep learning models for player trajectory prediction.
method Sparse trajectory prediction and constant acceleration interpolation.
result Interpolation improves performance for all tested models.
WS-II algorithm segments trajectories with high accuracy.
problem Trajectory segmentation for diverse data sources.
method Supervised learning with sliding window analysis.
result WS-II outperforms other methods in all datasets.
A framework clusters vehicle motion trajectories efficiently.
problem Costly manual annotation of vehicle motion data.
method Five-stage framework: align, embed, extract, embed, cluster.
result Framework achieves promising results on real-world dataset.
Proposes a CNN-based method for better trajectory owner prediction.
problem Improves trajectory owner prediction for better personalized recommendations and urban planning.
method Connects POIs in a graph, encodes POIs into vectors, transforms trajectories into matrices, and uses a CNN to detect features and predict owners.
result Significantly outperforms existing methods in various metrics.
EntroPath learns manifold geometry from diffusion paths.
problem Learning geodesic geometry from data graphs with spurious shortcuts.
method Maximum Entropy Path Ensemble Embedding (MERW) with k-step diffusion paths.
result EntroPath converges to squared geodesic distance in the short-time limit.
In this paper we propose a new parameter-free method for trajectory classification which finds the best trajectory partition and dimension combination for robust trajectory classification. Preliminary experiments show that our approach is very promising.
Generative model learns vehicle trajectory distributions for better data generalization.
problem Data sparsity and privacy issues in urban vehicle trajectory analysis.
method Generative adversarial imitation learning framework for urban vehicle trajectory generation.
result TrajGAIL model produces synthetic trajectories similar to real ones, achieving significant performance gains.
Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction and optimization. Interestingly, most all prior work in imitation and reinforcemen…
CoverNet predicts urban driving trajectories using diverse sets of possible actions.
problem Multimodal probabilistic trajectory prediction for urban driving.
method Frame trajectory prediction as classification over a diverse set of trajectories; dynamically generate sets based on current state.
result Outperforms state-of-the-art methods on real-world self-driving datasets.
Method detects trajectory outliers using Hodge Laplacian embeddings.
problem Detecting outliers in trajectory data on simplicial complexes.
method Flow-embeddings using Hodge 1-Laplacian of simplicial complexes.
result Classifies trajectories based on topological behavior.