Lie group integrators improve global error estimates.
problem Global error estimates for Lie group integrators.
method Relate local error to global error, derive from bounds.
result Lie-Butcher theory proves global error estimates for Lie group integrators.
Global optimality conditions found for deep neural networks.
problem Understanding the error landscape of deep neural networks.
method Analyzing deep linear and nonlinear neural networks with squared error loss.
result Necessary and sufficient conditions for global optimality in deep linear networks, with an efficiently checkable test.
Global optimization for hybrid system identification problems.
problem Switching linear regression and bounded-error estimation in hybrid systems.
method Branch-and-bound strategy with efficient lower bounds for continuous optimization.
result Global optimality is always guaranteed with scalable algorithms.
The study analyzes and mitigates errors in PC-based causal discovery methods.
problem Errors in PC-based causal discovery methods can lead to incorrect graphs.
method The study introduces coherency scores to detect assumption violations and small sample errors in PC-based methods.
result The coherency scores can detect errors that other methods cannot, bridging between global and local error detection.
Accelerates convergence in global non-convex optimization with reversible diffusion.
problem Global non-convex optimization challenges.
method Utilizes reversible diffusion processes with adaptive diffusion coefficients.
result Accelerated convergence with reduced discretization error.
GRAF uses global partitioning to improve ensemble classifier performance.
problem Improving ensemble classifier performance.
method GRAF extends oblique decision trees to global partitioning.
result GRAF reduces generalization error and improves performance on benchmark datasets.
The problem of estimation error of Expected Shortfall is analyzed, with a view of its introduction as a global regulatory risk measure.
Develops a chain rule for ReLU networks and extends approximation theory to global error estimates.
problem Applying standard chain rule to ReLU networks and extending approximation results globally.
method Introduces a derivative for ReLU networks and converts bounded domain results to global estimates.
result Extends neural network approximation theory to include regularity properties for ReLU networks.
JSRT improves regression tree performance by incorporating global node information.
problem Regression tree performance relies on local node means, ignoring global node information.
method Proposes JSRT by integrating global mean information from different nodes.
result Demonstrates superior performance and efficiency compared to other regression tree methods.
Analyzes error sources in global feature effect estimation methods.
problem Unexplored error sources in global feature effect estimation methods.
method Systematic, estimator-level analysis of bias and variance.
result Holdout data is theoretically cleanest, but estimation variance depends on sample size and model characteristics.
New method trains neural networks with local error signals, outperforming global methods.
problem Training neural networks with global error signals.
method Layer-wise training with local error signals.
result Layer-wise training with local error signals can approach state-of-the-art performance.
Adaptive method improves prediction intervals with global coverage guarantees and local error distribution.
problem Global coverage guarantees of conformal regression are often violated by local error distributions.
method Adaptive Conformal Regression with Jackknife+ Rescaled Scores
result Improves local coverage without sacrificing global coverage, especially in low-data regimes.
Clustering stocks reduces estimation error in global minimum variance portfolio.
problem High estimation error in covariance matrix estimation.
method Bounded clustering to limit maximum cluster size.
result Reduction in out-of-sample volatility and gap between in-sample and out-of-sample volatility.
New Taylor method proves periodic 3-body problem solution.
problem Existence of periodic solutions in the 3-body problem.
method A small variation of the Taylor method with global error formula.
result Rigorous proof of periodic solution existence.
A network of spiking agents learns complex tasks using global reward signals.
problem Solving complex reinforcement learning tasks.
method A hierarchical network of GLM spiking agents, each modulating its firing policy based on local and global reward signals.
result A network of spiking agents can learn complex action representations to solve RL tasks.
A new algorithm optimizes L1-norm error fitting problems efficiently.
problem Optimizing L1-norm error fitting models with data aggregation.
method Data aggregation-based algorithm with monotonic convergence to global optimum.
result The proposed algorithm optimally solves any L1-norm error fitting model.
The study analyzes how covariance estimation errors affect the global minimum-variance portfolio under heavy-tailed distributions.
problem The impact of covariance estimation errors on the global minimum-variance portfolio under heavy-tailed distributions.
method Characterization of covariance-estimation error's effect on GMVP suboptimality, derivation of regret identity and bound, application to heavy-tailed returns.
result The decision geometry of GMVP regret is invariant to a (p-1)-dimensional projection of the error matrix, with invariance to the covariance-scale direction as an exact special case.
Improved LMP algorithm for better sensor network estimation in non-uniform noise.
problem Improving distributed estimation in sensor networks with non-uniform noise.
method Weighted sum of mean square error cost function and steepest-descent recursion for weight updates.
result Advantages over diffusion LMP in non-uniform noise conditions.
A hybrid loss framework improves time series forecasting by balancing global and component errors.
problem Current time series methods may prioritize less significant sub-series, leading to forecasting bias.
method Proposes a hybrid loss framework combining global and component losses, dynamically adjusting weights.
result Improves time series forecasting performance by 0.5-2% on average.
We efficiently find top k eigenvectors in streaming PCA with global convergence.
problem Finding top k eigenvectors in streaming PCA with limited space.
method Developed global convergence for Oja's algorithm and a faster variant Oja++.
result Achieved global convergence rate matching information theoretic lower bound.
GAAVI offers anytime-valid tests for CMF global null and contrasts.
problem Inference on the conditional mean function for high confidence decisions.
method Asymptotic anytime-valid tests for CMF global null and contrasts.
result Achieves asymptotic type-I error guarantees, power one, and optimal sample complexity.
New estimates show local covering estimates determine error rates in convex function learning.
problem Learning error rates in convex function classes with independent noise.
method Established new upper and lower bounds on error rates using local covering estimates.
result Error rates are determined by local covering estimates, not gaussian averages.
SEARNN improves RNN training by incorporating global-local losses.
problem RNNs trained with MLE fail to exploit structured losses and suffer from exposure bias.
method SEARNN introduces global-local losses through test-alike search space exploration.
result SEARNN outperforms MLE on OCR, spelling correction, and machine translation tasks.
Replica exchange Langevin diffusion accelerates nonconvex optimization.
problem Nonconvex optimization challenges in machine learning.
method Replica exchange Langevin diffusion, discretization analysis.
result Replica exchange accelerates convergence to global minima.
Neural TD and Q-learning prove to converge globally to optimal solutions.
problem Nonconvexity and divergence in neural TD due to value function approximation.
method Proving global convergence of neural TD and Q-learning using overparametrization of neural networks.
result Neural TD and Q-learning converge globally to the global optimum of mean-squared projected Bellman error.
New algorithm optimizes robust estimation under mixed local and global corruptions.
problem Combining local and global corruptions in robust statistics.
method Information-theoretic approach using sliced-Wasserstein metric.
result Optimal error achieved in polynomial time for stronger local perturbations.
Wide CNNs with shared weights and max pooling have linearly independent features and can achieve zero training error.
problem Understanding the optimization landscape and expressiveness of deep CNNs.
method Analysis of loss landscape and expressiveness of practical deep CNNs with shared weights and max pooling layers.
result Wide CNNs can achieve zero training error and have a well-behaved loss surface with almost no bad local minima.
Study compares local and global models for hierarchical forecasting accuracy.
problem Challenges in hierarchical time series forecasting, especially in accuracy and information utilisation.
method Developed and evaluated local and global forecasting models (GFMs) to exploit cross-series and cross-hierarchies information.
result Global Forecasting Models (GFMs) outperform local models in hierarchical forecasting accuracy and computational efficiency.
Bayesian neural networks detect complex interactions with uncertainty.
problem Estimating global pairwise interaction effects with uncertainty.
method Bayesian neural network for modeling interactions, GEH for estimating interaction effects.
result The method empirically outperforms alternatives and detects interpretable interactions.
Gradient descent can solve shallow neural network training problems globally.
problem Training shallow linear neural networks.
method Analyzed the geometric properties of the loss landscape.
result Gradient descent can converge globally due to the landscape's properties.
Framework verifies global correctness of neural networks for perception tasks.
problem Verifying robustness of neural networks is insufficient; global correctness needs to be ensured.
method Specified a state space and observation process to define the target input space. Tiled the spaces and compared ground truth and network output bounds to deliver error bounds.
result Framework can verify error bounds globally over the target input space and detect illegal inputs.
Paper compares ARMA with exogenous variables to Gradient Boosting Regression for electricity price forecasting.
problem Energy price forecasting is hard and multi-step time series forecasting.
method ARMA with exogenous variables vs. Gradient Boosting Regression
result Gradient Boosting Regression outperforms ARMA with exogenous variables in terms of error metrics.
GIV methodology extends instrumental variable estimation for high-dimensional data.
problem Estimating structural parameters in high-dimensional models with endogeneity and latent factors.
method Extends GIV methodology to large N and T, treats factors and loadings as unknown, and uses additional instruments for efficiency.
result Efficiency gains and negligible sampling errors in estimated instrument and factors.
Paper solves open problem of first-order algorithms for filtering-clustering models.
problem Understanding convergence property of first-order algorithms for filtering-clustering models.
method Identifies a global error bound condition and designs a generalized dual gradient ascent algorithm.
result Proposes optimal first-order algorithms in deterministic, finite-sum, and online settings.
Distributed learning with least squares regularization achieves good performance without eigenfunction assumptions.
problem Efficiently learning from large datasets distributed across multiple machines.
method Divide-and-conquer approach, least squares regularization, RKHS, error bounds in expectation.
result The global estimator is a good approximation to the full data estimator, with sharp error bounds.
New diffusions help globally optimize non-convex functions.
problem Optimizing non-convex functions globally.
method Euler discretization of Langevin diffusion.
result Different diffusions optimize different convex and non-convex functions.
Neural networks can approximate complex stochastic equations well.
problem Approximating general stochastic differential equations.
method Identified neural network classes approximating continuous functions.
result Neural stochastic differential equations can approximate general stochastic differential equations arbitrarily well.
New approach trains neural networks using CSP-solving techniques.
problem Training recurrent neural networks efficiently.
method Converts training set to CSP, solves using QGS.
result QGS finds global minimum without local minima.
Paper tackles fairness in CCA by minimizing correlation disparity error.
problem Fairness issues in CCA.
method Framework to minimize correlation disparity error in CCA.
result Reduces correlation disparity error without sacrificing CCA accuracy.
New algorithm trains deep neural networks without global optimization.
problem Training deep neural networks efficiently and without global optimization.
method Uses random complex exponential activation functions and Markov Chain Monte Carlo sampling.
result Consistently attains theoretical approximation rate for residual networks.
SeqRF straightens generative model flows to speed up sampling.
problem High global truncation error in ODE-based solvers for generative models.
method SeqRF, a learning technique that straightens the probability flow.
result Significantly improved sampling speed and synthesis quality.
Paper uses DFL to optimize portfolio risk and outperforms conventional methods.
problem Optimizing portfolio risk and return under uncertainty.
method Decision-focused learning (DFL) to derive global minimum variance portfolio (GMVP).
result DFL-based methods consistently deliver superior decision performance in portfolio optimization.
This work analyzes policy gradient methods in reinforcement learning, providing convergence and approximation guarantees.
problem Theoretical convergence and approximation error of policy gradient methods in reinforcement learning.
method Analysis of policy gradient methods in discounted MDPs, focusing on tabular and parametric policy classes.
result Provably characterizations of computational, approximation, and sample size properties of policy gradient methods.
A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such minimizations, and it is often thought that a main source of difficulty for these l…
New method shows AdaGrad converges globally to neural network minima.
problem Convergence of adaptive gradient methods for neural networks.
method Proposed adaptive gradient method for over-parameterized neural networks.
result Converges to global minimum in polynomial time for two-layer networks.
Establishes unique weak solution to complex flow on smooth manifolds.
problem Existence of weak solutions to complex flow equations.
method Applying viscosity theory to prove existence of unique solution.
result Unique global weak solution exists for smooth manifolds.
Federated learning models are analyzed through game theory to determine optimal model sharing.
problem Agents with different data distributions face a choice between local or global models in federated learning.
method The problem is analyzed using coalitional game theory and hedonic game theory, considering different degrees of customization in model sharing.
result Exact expected MSE values are derived for linear regression and mean estimation problems, and stable partitions of players into coalitions are analyzed.
New framework analyzes deep learning optimization with finite width networks, revealing generalization gaps and excess risks.
problem Analyzing generalization error of deep learning with finite width networks.
method Formulating neural network training as transportation map estimation and analyzing via infinite dimensional Langevin dynamics.
result Achieves fast learning rate and minimax optimal rates for classification and regression problems.