Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
New algorithms minimize cost while identifying the best alternative quickly.
problem Balancing cost minimization and best arm identification in online learning.
method Developed algorithms that are delta-PAC and minimize regret, providing theoretical guarantees.
result Proved algorithms that balance cost and decision time, improving A/B testing.
New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.
problem Uncertainty quantification in online settings with changing data distributions.
method Developed new online conformal prediction methods that minimize strongly adaptive regret.
result Achieve near-optimal strongly adaptive regret and approximately valid coverage.
Paper analyzes time series prediction using empirical risk minimization.
problem Optimizing 1-step-ahead prediction for time series.
method Empirical risk minimization applied to recursive algorithms for time series forecasting.
result Empirical risk minimization achieves optimal predictive performance.
Minimal assumptions analysis of Q-learning with time-varying policies.
problem Finite-time analysis of Q-learning with time-varying policies for discounted MDPs.
method Minimal assumptions, Poisson equation decomposition, sensitivity analysis.
result Established convergence rate and sample complexity for Q-learning.
Paper tackles fairness in machine learning models by preventing representation disparity over time.
problem Representation disparity in machine learning models leading to unfairness over time.
method Develops a distributionally robust optimization (DRO) approach to minimize worst-case risk.
result Demonstrates that DRO prevents disparity amplification and improves minority group satisfaction.
Deep learning approach for efficient semantic segmentation on low-power devices.
problem Challenges in applying deep learning to small mobile robots with minimal hardware.
method Semantic segmentation approach on a low-power mobile processor.
result Achieves real-time processing of full VGA images on low-power mobile processors.
New machine learning paradigm ignores loss function until action time.
problem Learning with unknown loss functions.
method Introduces omnipredictors for any loss function.
result Extracts predictive power from any class, ignoring loss function.
Enhances neural networks for regression tasks with minimal learning time increase.
problem Improving performance of neural networks in regression tasks.
method Extends the learning procedure of a neural network to improve its performance without changing the prediction.
result The modified model performs better than the original model with minimal learning time increase.
A new algorithm for minimizing functions on Wasserstein space.
problem Discretization of continuous Wasserstein gradient flows in machine learning.
method Forward-Backward discretization scheme for minimizing functions with smooth and nonsmooth components.
result The FB scheme converges similarly to proximal gradient algorithms in Euclidean spaces.
Study minimal time-like surfaces in 4D space-time, proving conditions for existence.
problem Characterize minimal time-like surfaces in 4D space-time.
method Apply complex analysis over double numbers to classify surfaces and derive natural equations.
result Existence and uniqueness of minimal time-like surfaces based on curvature conditions.
DRIO improves time series imputation by minimizing reconstruction error and distributional divergence.
problem Bias in imputation due to mismatch between observed and true data distributions.
method DRIO minimizes reconstruction error and worst-case divergence using Wasserstein ambiguity set.
result DRIO consistently provides robust imputation and improved forecasting.
First order methods can take extremely long to find global minima of non-convex functions.
problem Finding global minimizers of non-convex functions.
method Designing a family of non-convex functions and using statistical lower bounds for parameter estimation.
result First order methods can take exponential time to converge to a global minimizer.
Proves existence of a strategy to minimize shortfall for game options.
problem Minimizing shortfall for game options in discrete time.
method Proves existence of a self-financing strategy.
result Existence of a self-financing strategy to minimize shortfall for game options in discrete time.
New algorithm learns optimal policies with minimal memory and time.
problem Learning optimal policies in discounted MDPs with short burn-in time.
method Variance reduction and adaptive policy switching.
result First regret-optimal model-free algorithm with low burn-in time.
Protocol learns pure quantum states with minimal disturbance.
problem Efficiently learn quantum states with minimal disturbance.
method Sequential measurements with minimal disturbance.
result Achieves maximal precision with polylogarithmic regret.
Minimal hypersurfaces with cylindrical tangent cones constructed and analyzed.
problem Constructing minimal hypersurfaces with specific geometric properties.
method Constructing minimal hypersurfaces with cylindrical tangent cones and proving unique continuation results.
result Existence and properties of minimal hypersurfaces with cylindrical tangent cones.
Optimal batch size minimizes training time for neural networks.
problem Minimizing training time for two-layer neural networks with SGD.
method Characterized optimal batch size as a function of target hardness (information exponents). Used Correlation loss SGD to overcome limitations.
result Optimal batch size minimizes training time without changing total sample complexity.
CMoS improves time series forecasting with minimal parameters.
problem Efficiently forecasting time series data with limited resources.
method CMoS directly models chunk-wise spatial correlations, using Correlation Mixing and Periodicity Injection techniques.
result CMoS outperforms state-of-the-art models with minimal parameters.
New method learns models to adapt to domain shifts at test time.
problem Learning models robust to distribution shifts in practical applications.
method Adaptive Risk Minimization (ARM) framework.
result Performance gains of 1-4% on image classification problems.
New method learns vector fields from noisy time series data.
problem Learning vector fields from noisy time series data.
method Neural network architecture with tensor products of one-dimensional neural shape functions for vector field approximation, alternating minimization for noise handling.
result Neural shape function architecture robust to noise, learning accurate vector fields from data with up to 10% Gaussian noise.
Unified analysis of stochastic ADMM variants via SME.
problem Analyzing and optimizing stochastic ADMM variants for machine learning.
method Unified mathematical framework of SME for continuous-time analysis.
result Dynamics of stochastic ADMM approximated by SDEs with small noise.
Develops a new learning framework for dynamic data.
problem Poor performance of existing strategies in dynamic data and goals.
method Prospective Learning framework and Prospective ERM algorithm.
result Prospective ERM converges to Bayes risk under certain assumptions.
WOODS benchmarks improve understanding of time series OOD generalization.
problem Limited understanding of OOD generalization in time series.
method Presented eight open-source time series benchmarks and revised OOD algorithms.
result Large room for improvement in OOD generalization algorithms for time series.
A new deep learning method for option pricing in rough volatility models.
problem Efficient pricing of European options in high-dimensional rough volatility models.
method Time-stepping deep gradient flow method reformulating the option pricing PDE as an energy minimization problem.
result The method respects asymptotic behavior and known bounds for option prices.
Extended LPCMCI learns causal models from interventional data to minimize prediction error.
problem Optimizing prediction of target variables using causal models.
method Combining observational and interventional causal discovery methods.
result Extended LPCMCI allows 60.9% optimal prediction of target variables compared to 53.6% with original LPCMCI.
Solves PDE system for minimal space-like surfaces in Minkowski space-time.
problem Solving the system of natural PDE's for minimal space-like surfaces.
method Using canonical Weierstrass representations, solves the system explicitly.
result Expresses solutions by means of two holomorphic functions.
Minimal hypersurfaces in spheres generated by isoparametric foliations are found.
problem Existence of minimal hypersurfaces in spheres generated by isoparametric foliations.
method Generalized rotational ansatz formed by the union of homothetic copies of isoparametric leaves, reducing the minimal surface equation to an ordinary differential equation.
result Closed embedded minimal hypersurfaces of topological type S1imesM are found for any isoparametric hypersurface M⊂Sn. This work tackles domain generalization by minimizing discrepancy between domains.
problem Domain generalization: learning to handle unseen domains with i.i.d. data assumptions violated.
method The approach involves minimizing discrepancy between domains using a lemma and deriving a generalization bound.
result Low risk over unseen domains can be achieved by representing data in a space where training distributions are indistinguishable and relevant information is preserved.
New findings on computational complexity of ERM problems.
problem Understanding the computational complexity of ERM problems.
method Conditional hardness results based on complexity-theoretic assumptions.
result No algorithms can solve ERM problems to high accuracy in sub-quadratic time under certain assumptions.
SGLD helps escape local minima in non-convex learning problems.
problem Non-convex optimization in machine learning.
method Stochastic Gradient Langevin Dynamics with Gaussian noise.
result Finite-time guarantees for SGLD to find approximate minimizers.
New algorithm solves online resource allocation problems efficiently.
problem Dynamic resource allocation in operations research.
method Minimal Selection Principle and MSoE algorithm.
result Ensures optimal cumulative regret bounds in dynamic resource allocation.
Efficiently completes low-rank matrices with nearly linear time complexity.
problem Completing low-rank matrices from a few observed entries.
method Robust alternating minimization framework with approximate updates.
result Achieves nearly linear time complexity in matrix completion.
TD learning reduces prediction error in Markov chain problems.
problem Estimating value functions in Markov chains with temporal inconsistency.
method Temporal difference learning minimizes temporal inconsistency between successive estimates.
result TD learning can significantly reduce mean-squared error in value estimates.
This paper proposes faster machine learning by reducing data access time.
problem Slow training times due to large datasets or feature sizes.
method Systematic and cyclic sampling techniques to reduce data access time.
result Proven to reduce training time up to six times with empirical validation.
Adaptive approach for cost-effective prediction models.
problem Resource-constrained prediction with accuracy and cost trade-offs.
method Bottom-up strategy to learn gating and prediction models.
result Method achieves higher accuracy with lower cost compared to state-of-the-art.
Canonical coordinates defined for minimal time-like surfaces in n-dimensional Minkowski space.
problem Characterizing canonical coordinates on minimal time-like surfaces.
method Introducing canonical coordinates and proving their existence and uniqueness; using analysis over the algebra of double numbers.
result Canonical coordinates on minimal time-like surfaces are characterized by a natural condition for a complex function over the algebra of double numbers.
Continuous-time SGD converges under certain conditions, useful for deep learning.
problem Minimizing population expected loss in learning problems.
method Continuous-time approximation of stochastic gradient descent.
result Establishes sufficient conditions for convergence, applicable to overparametrized neural networks.
This study examines abnormal geodesics in 2D-Zermelo navigation problems, revealing their role in separating time minimal and maximal curves.
problem The role of abnormal geodesics in planar Zermelo navigation problems with strong current.
method Geometric time optimal control approach, focusing on the heading angle of the ship.
result Abnormal geodesics separate time minimal and maximal curves, and are both small-time minimizing and maximizing.
A new model minimizes investment risk at multiple time points.
problem Minimizing risk in investment portfolios with multiple stopping points.
method Developed a multi-time state mean-variance model using Riccati equations.
result Optimal investment strategies can be derived from a sequence of Riccati equations.
We propose a new method for the construction of Hamiltonian-minimal and minimal Lagrangian immersions of some manifolds in Cn and in CPn. By this method one can construct, in particular, immersions of such manifolds as the generalized Klein's bottle Kn, the multidimensional torus, Kn−1×S1, $S^{n-1}…
New time series generation models improve accuracy and correlation identification.
problem Generating accurate and correlated time series from limited data.
method Conditional Euler Generator (CEGEN) using Euler discretization of SDEs and Wasserstein metrics.
result CEGEN outperforms state-of-the-art models on various metrics and real-world datasets.
Model learns tensor representations from imperfect multimodal data.
problem Learning from imperfect multimodal data with noise or missing entries.
method Tensor rank minimization to regularize rank of tensor representations.
result Model effectively learns tensor representations from imperfect data.
We recast the Calabi flow in DeGiorgi's language of minimizing movements. We establish the long time existence of minimizing movements for K-energy with arbitrary initial condition. Furthermore we establish some a priori regularity of these solutions, and that sufficiently regular minimizing movements are smooth soluti…
Federated learning optimizes task and resource allocation in balloon networks.
problem Minimizing energy and time consumption in task computation and transmission.
method SVM-based federated learning algorithm to dynamically adjust user associations, service sequences, and task allocations.
result Reduces the weighted sum of energy and time consumption by up to 16.1%.
The paper proves the regularity of cohomogeneity two problems and constructs minimal hypersurfaces on spheres.
problem Cohomogeneity two equivariant isotopy minimization problems and minimal hypersurfaces with large Betti numbers.
method Developed cohomogeneity two equivariant min-max theory for minimal hypersurfaces.
result Constructs minimal hypersurfaces on spheres with large Betti numbers and specific symmetries.
Constructs perturbations of a minimal surface with triple junctions.
problem Minimal surfaces with triple junctions in curved spaces.
method Constructs stationary perturbations with given boundary conditions.
result Constructs minimal surfaces with triple junctions in R2imesS1.