Dynamic CBDT improves treatment effect estimation in clinical data.
problem Estimating heterogeneous treatment effects in observational data with high accuracy and interpretability.
method Dynamic Regularized Causal Boosted Decision Trees (CBDT) integrating variance regularization and calibration.
result Significantly improved estimation accuracy and reliable coverage of true treatment effects.
Novel model captures high-dimensional copulas with spectral dynamics and regularization.
problem Modeling time-varying, asymmetric, tail-dependent copulas in high dimensions.
method Score-driven dynamics for eigenvalues, non-linear shrinkage for biases, parsimonious and scalable.
result Model outperforms recent alternatives in capturing co-movements and diversification potential.
Study L2 regularization in deep networks, uncovering performance relations and proposing a training schedule.
problem Understanding and optimizing L2 regularization in deep learning models. method Empirical observations and theoretical analysis of gradient flow dynamics in infinitely wide networks.
result Empirical relations between model performance, L2 coefficient, learning rate, and training steps; optimal regularization parameter prediction; improved training schedule. This work introduces the concept of tangent space regularization for neural-network models of dynamical systems. The tangent space to the dynamics function of many physical systems of interest in control applications exhibits useful properties, e.g., smoothness, motivating regularization of the model Jacobian along sys…
AIR-Net adapts low-rank regularization dynamically for better image completion.
problem Fixed low-rank regularization limits adaptability to different images.
method AIR-Net uses adaptive and implicit regularization parameterized by a dynamic Laplacian matrix.
result AIR-Net enhances implicit regularization and outperforms fixed methods in non-uniform missing data scenarios.
Paper adds Fisher Information to mean field optimization for faster convergence.
problem Mean field optimization in neural networks training.
method Developed energy-dissipation method and gradient flow on probability space.
result Marginal distributions converge exponentially to minimizer.
Enhances RSCNs with hybrid regularization for nonlinear dynamics.
problem Modeling nonlinear dynamic systems with uncertainties.
method Recurrent stochastic configuration networks with hybrid regularization.
result The method outperforms other models in nonlinear system identification and industrial tasks.
New insights into how deep models generalize, focusing on matrix factorization.
problem Understanding how deep models generalize and why they work well.
method Using Morse functions and dynamical systems to study implicit regularization.
result Solved a conjecture on implicit regularization in matrix factorization.
Study non-Weinstein Liouville geometry via hyperbolic dynamics, proving rigidity results.
problem Characterize non-Weinstein Liouville geometry with persistent transverse skeleton.
method Anosov 3-flows, Liouville Interpolation Systems, non-singular partially hyperbolic flows, hyperbolic dynamics.
result Mitsumatsu's examples characterize 4D non-Weinstein Liouville geometry with 3D persistent transverse skeleton.
Formula derived for zeta functions of 3D foliated systems.
problem Analyzing zeta functions of 3D Riemannian foliated dynamical systems.
method Relating dynamical spectral ξ-functions to zeta functions using the distributional dynamical Lefschetz trace formula. result Proved a regularized determinant formula for zeta functions.
Paper proposes a new dynamic pricing method with always-valid online statistical learning.
problem Designing dynamic pricing policies that adapt to online uncertainty and maintain validity.
method Regularized online statistical learning with theoretical guarantees and three major advantages.
result Proposed OORMLP pricing policy secures logarithmic regret in decision horizon.
Machine learning identifies chimera states in complex dynamical systems.
problem Chimera states are hard to identify due to their varied appearance and peculiar nature.
method Machine learning techniques, specifically random forest and oblique random forest with null space regularization.
result High accuracy in identifying chimera states across different dynamical models.
Method improves SINDy for noisy nonlinear systems.
problem Recover nonlinear dynamical systems from noisy data.
method Reweighted ℓ1-regularized least squares. result Improved accuracy and robustness in noisy conditions.
We reparametrize ReLU NNs as splines to understand their learning dynamics.
problem Understanding the learning dynamics and inductive bias of neural networks.
method Reparametrize ReLU NNs as continuous piecewise linear splines to study learning dynamics.
result Standard weight initializations yield very flat functions, leading to strength and type of implicit regularization.
A new screening rule 'dynamic Sasvi' improves sparse optimization speed.
problem Sparse optimization problem identification.
method Flexible framework based on Fenchel-Rockafellar duality for norm-regularized least squares.
result Dynamic Sasvi can eliminate more features and increase solver speed.
New method for optimistic planning in MDPs using regularization.
problem Optimistic planning in infinite-horizon discounted MDPs.
method Regularized dynamic programming for approximate value iteration.
result Achieves near-optimal statistical guarantees in learning policies.
New algorithm speeds up path computation for optimal models.
problem Finding the exact path of optimal models from a finite set.
method Dynamic programming approach for linear time computation.
result Dynamic programming achieves linear time for breakpoints computation.
Diffusion models' sampling paths lie in a low-dimensional subspace, resembling boomerangs.
problem Understanding the geometric structure of diffusion-based generative models.
method Characterization of deterministic sampling trajectories using low-dimensional subspace and kernel-estimated data modeling.
result Sampling trajectories in diffusion models are confined to a low-dimensional subspace and exhibit a boomerang shape.
A simple regularization technique speeds up training of Neural ODEs.
problem Training Neural ODEs is computationally expensive.
method Randomly sampling the end time of the ODE during training.
result Significantly decreases training time and improves performance.
Paper studies generic dynamics of MCFs with spherical singularities.
problem Characterizing the generic behavior of mean curvature flow with spherical singularities.
method Level set formulation of mean curvature flow, analysis of arrival time function.
result Generically, the arrival time function has at most C2 regularity. Symmetry-regularized Neural ODEs improve model stability and interpretability.
problem Improving the stability and physical interpretability of Neural ODEs.
method Integrating Lie symmetries and conservation laws into the loss function.
result Symmetry-regularized Neural ODEs enhance model stability and interpretability.
New method trains neural ODEs faster with fewer layers.
problem Training neural ODEs on large datasets is computationally expensive.
method Combines optimal transport and stability regularizations.
result Significant reductions in training time with no performance loss.
New Langevin dynamics samples from entropy-regularized optimal transport.
problem Sampling from entropy-regularized optimal transport.
method Introduced analogous diffusion dynamics constrained to Π(μ,ν). result Long-time limit is the unique solution of an entropic optimal transport problem.
AER dynamically adjusts entropy regularization for better LLM reinforcement learning.
problem Policy entropy collapse in RLVR training limits exploration and reasoning performance.
method Adaptive Entropy Regularization (AER) with difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.
result AER consistently outperforms baselines on mathematical reasoning benchmarks, improving both accuracy and exploration.
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
Theory of Newtonian dynamical systems admitting normal shift of hypersurfaces was first developed for the case of Riemannian manifolds. Recently it was generalized for manifolds geometric equipment of which is given by some regular Lagrangian or, equivalently, by some regular Hamiltonian dynamical system. In present pa…
Geometrically transforms nonconservative dynamics to linearize Kepler and Manev systems.
problem Regularizing and linearizing nonconservative central force dynamics.
method Projective transformation and conformal scaling in configuration and phase spaces.
result Full linearization of Kepler and Manev dynamics in any finite dimension.
HCLM framework uses entropy regularization for open learning systems.
problem Real-world AI challenges and limitations of deep learning.
method Dynamical and information-theoretic framework with entropy regularization.
result Geometric entropy surrogates, especially log-determinant covariance entropy, induce stronger and more stable information forces.
Large SGD step sizes lead to sparse feature learning in neural networks.
problem Sparse feature learning in neural networks with large step sizes.
method Empirical observations and theoretical analysis of SGD dynamics.
result Large step sizes induce implicit regularization leading to sparse predictors.
KL-regularized RL from expert demos can lead to slow, unstable learning.
problem Pathological training dynamics in KL-regularized RL from expert demonstrations.
method Empirical analysis and non-parametric behavioral reference policies.
result KL-regularized RL can be significantly improved by using non-parametric behavioral policies.
We learn linear models from nonlinear systems using multiple trajectories and regularization.
problem Identifying linear models from data when the underlying dynamics are nonlinear.
method Multiple trajectories data acquisition followed by regularized least squares.
result Learn linearized dynamics with arbitrarily small error given enough samples.
Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data. Learned dynamics models can be directly used for planning actions but this has been challenging because of inaccuracies in the learned …
The dynamic ensemble selection of classifiers is an effective approach for processing label-imbalanced data classifications. However, such a technique is prone to overfitting, owing to the lack of regularization methods and the dependence of the aforementioned technique on local geometry. In this study, focusing on bin…
This paper studies nonholonomic constraints in Hamiltonian systems, deriving equations and theorems.
problem Analyzing nonholonomic constraints in Hamiltonian systems.
method Deriving distributional RCH systems, geometric constraint conditions, and Hamilton-Jacobi theorems.
result Derives precise geometric constraint conditions and Hamilton-Jacobi theorems for nonholonomic systems.
CLSB models system dynamics from cross-sectional data with population-level regularization.
problem Challenges in modeling system dynamics from limited cross-sectional samples and heterogeneous individual behaviors.
method Introduces CLSB framework for learning dynamics, regularized for population-level temporal variations.
result Empirically superior in single-cell sequencing data analyses, e.g., simulating cell development and drug response.
Generative adversarial network for probabilistic forecasting of random systems.
problem Forecasting random dynamical systems without distributional assumptions.
method Recurrent neural network and generative adversarial network (GAN) with regularization based on maximum mean discrepancy (MMD).
result The proposed model successfully forecasts complex stochastic processes with multiple-step predictions.
The paper proves regularity of states on manifolds with unstable dynamics.
problem Propagation of regularity in dynamical systems with unstable manifolds.
method Leafwise semiclassical pseudodifferential calculus adapted to foliated spaces.
result Pollicott-Ruelle resonant states are smooth over entire manifolds if smooth on unstable leaves.
Sparse model selection is ubiquitous from linear regression to graphical models where regularization paths, as a family of estimators upon the regularization parameter varying, are computed when the regularization parameter is unknown or decided data-adaptively. Traditional computational methods rely on solving a set o…
A main theoretical interest in biology and physics is to identify the nonlinear dynamical system (DS) that generated observed time series. Recurrent Neural Networks (RNNs) are, in principle, powerful enough to approximate any underlying DS, but in their vanilla form suffer from the exploding vs. vanishing gradients pro…
The paper develops a new approach to solve vector-valued PDEs on manifolds with minimal regularity.
problem Well-posedness and Lp-based Sobolev regularity of vector-valued PDEs on compact manifolds. method Develops a parametrization-free variational approach using classical results in reflexive Banach spaces.
result Establishes higher-order Wm,p regularity for vector-valued PDEs on manifolds of minimal regularity. Study on how optimal representations emerge during deep learning training, focusing on the role of implicit regularization.
problem Understanding how optimal representations for tasks are learned during training.
method Investigates the role of implicit regularization in learning minimal sufficient representations, analyzing changes in representation content during training.
result Semantically meaningful but ultimately irrelevant information is encoded in early transient dynamics of training, which is later discarded.
In this paper, we give concrete descriptions of leafwise cohomology groups and show the regularized determinant expression of the dynamical zeta function for fiber bundles over S1. As applications, we show a functional equation and some formulas for special values of the dynamical zeta function.
RLD improves combinatorial optimization by avoiding local minima.
problem Efficiently solving combinatorial optimization problems.
method Regularized Langevin Dynamics (RLD) for combinatorial optimization.
result RLD achieves comparable or better performance than previous methods.
New method learns adaptive exploration strategies for dynamic tasks.
problem Learning effective exploration strategies in changing environments.
method Informed policy regularization to reduce sample complexity of RNN-based policies.
result Method learns efficient exploration strategies balancing information gathering and reward maximization.
In this paper, we give precisely the geometric constraint conditions of canonical symplectic form and regular reduced symplectic forms for the dynamical vector fields of a regular controlled Hamiltonian (RCH) system and its regular reduced systems, which are called the Type I and Type II of Hamilton-Jacobi equations. A…
New stability estimate for metric rigidity in hyperbolic dynamics.
problem Metric rigidity in hyperbolic dynamics.
method Radial source estimates in Hölder-Zygmund spaces for uniformly hyperbolic dynamics.
result Metrics with same marked length spectrum are isometric in C3+ε-close metrics in any dimension ≥2. This paper examines how Higher-Order Langevin Dynamics reduces memorization in diffusion models.
problem Memorization of training samples in diffusion models, violating copyright and privacy.
method Introduces Higher-Order Langevin Dynamics (HOLD) to regularize diffusion model trajectories.
result The dynamics of the data variable in HOLD are governed by a low-pass-filtered version of the learned score function, with smoothness increasing with model order.
Bayesian method for dynamic correlation matrices improves accuracy and responsiveness.
problem Challenges in estimating time-varying correlation matrices, including slow adaptation, insufficient regularization, and diffuse uncertainty.
method Low-rank factor representation with dynamic shrinkage prior and multivariate factor stochastic volatility model.
result Improved accuracy and responsiveness compared to competing methods in various challenging scenarios.