Study introduces new curvature conditions for Lorentzian spaces using Rényi entropy.
problem Developing synthetic curvature conditions for Lorentzian spaces.
method Introducing timelike curvature-dimension conditions and measure-contraction properties using Rényi entropy.
result Equivalence of new curvature conditions to entropic counterparts.
A new metric measures time series divergence efficiently.
problem Quantifying subtle differences in time series data.
method Sequence Likelihood (SL) divergence, a generalized KL divergence for time series.
result Efficient estimators of SL divergence from finite sample paths.
New method uses Floer homology to create exotic disk pairs.
problem Creating exotic disk pairs in 4-manifolds.
method Singular instanton Floer homology with Chern--Simons filtration.
result Constructs exotic pairs of slice disks and knots.
Investigation of the underlying physics or biology from empirical data requires a quantifiable notion of similarity - when do two observed data sets indicate nearly identical generating processes, and when they do not. The discriminating characteristics to look for in data is often determined by heuristics designed by …
Improved regret bound for multinomial logistic bandits with non-linearity.
problem Maximizing rewards in multinomial logistic bandits with non-linear feedback.
method Extended the definition of κ ∗ κ_* κ ∗ to multinomial setting and proposed an efficient algorithm. result Minimax-optimal regret bound of O ~ ( R d K T / κ ∗ ) \smash{\widetilde{\mathcal{O}}( R d \sqrt{ {KT}/{κ_*}} ) } O ( R d K T / κ ∗ ) , improving over existing guarantees. Improved regret bounds for bandit phase retrieval.
problem Minimizing cumulative and simple regret in a bandit phase retrieval problem.
method Proved minimax cumulative and simple regret bounds using adaptive algorithms.
result Minimax cumulative regret is i l d e Θ ( d n ) ilde{\Theta}(d \sqrt{n}) i l d e Θ ( d n ) and minimax simple regret is i l d e Θ ( d / n ) ilde{\Theta}(d / \sqrt{n}) i l d e Θ ( d / n ) . New algorithm improves multiclass classification regret bound.
problem Improving multiclass classification with bandit feedback.
method Developed a new bandit classification algorithm.
result Guaranteed regret of O ~ ( ∣ H ∣ + T ) \smash{\widetilde{O}(|H|+\sqrt{T})} O ( ∣ H ∣ + T ) , improving over classical algorithms. Geodesics found in spacetime satisfy curvature conditions.
problem Finding geodesics in spacetime satisfying specific curvature conditions.
method Proving existence of geodesics with entropic semiconvexity and uniform L ∞ L^\infty L ∞ densities. result Existence of geodesics satisfying the timelike curvature-dimension condition.
New method uses Chern-Simons filtration to study corks and bounding.
problem Studying strong corks and equivariant bounding invariants.
method Utilizes Chern-Simons filtration in instanton Floer homology.
result Examples of corks with specific properties.
Instanton Floer homology matches Heegaard Floer for almost-rational plumbings.
problem Matching instanton Floer homology with Heegaard Floer for specific 3-manifolds.
method Utilizes lattice homology and a recent cobordism map decomposition theorem.
result Isomorphism between framed instanton Floer homology and Heegaard Floer for almost-rational plumbings.
Improved regret bound for MNL MDPs with variance-aware approach.
problem Optimal reinforcement learning for MNL MDPs with structured variance.
method Introducing a problem-dependent constant measuring average variance, proposing an algorithm with improved regret bound.
result Minimax optimal regret bound of O ( d H 2 σ ˉ T T ) O(dH^2\barσ_T\sqrt{T}) O ( d H 2 σ ˉ T T ) for structured MDPs. Optimizes transport in Finsler spacetimes with lower Ricci bounds.
problem Optimizing transport in Finsler spacetimes with lower Ricci bounds.
method Using optimal transport and weighted Ricci curvature bounds.
result Proves timelike curvature-dimension condition for Finsler spacetimes.
Currents on Lie groups form a Hopf algebra structure.
problem Understanding algebraic structure of currents on Lie groups.
method Defined Hopf algebra structure on currents using convolution and wedge product.
result Explicit formulas for Hopf algebra operations on currents are derived.
Estimating signals with linear recurrence relations under Gaussian noise is nearly as hard as sparse signals.
problem Estimating discrete-time signals with unknown linear recurrence relations in Gaussian noise.
method Analyzing shift-invariant subspaces and their Fourier coefficients as reproducing filters.
result The statistical complexity is nearly the same as for s s s -sparse signals, and the estimator is tractable. The study proves timelike Ricci bounds for low regularity spacetimes using optimal transport.
problem Proving timelike Ricci bounds for spacetimes with low regularity.
method Using optimal transport to prove timelike measure-contraction property.
result Timelike curvature-dimension condition holds for C 1 , 1 \smash{\mathrm{C}^{1,1}} C 1 , 1 metrics. Study heat flow inequalities on 1-forms in RCD spaces.
problem Heat flow inequalities on 1-forms in RCD spaces.
method Analyzes heat flow ( H t ) (\mathsf{H}_t) ( H t ) and its properties on cotangent modules over RCD spaces. result Establishes various L p L^p L p -properties and spectrum inclusions for the heat flow. CSE-FSL reduces communication and storage costs in federated learning.
problem High communication and storage costs in federated learning.
method CSE-FSL uses an auxiliary network to locally update client models and sends only selected epochs' smashed data.
result Significant communication reduction with state-of-the-art convergence and model accuracy.
Minimum width for ReLU networks on compact domain is exactly max{d_x, d_y, 2}
problem Characterizing the minimum width for ReLU networks to approximate functions on compact domains
method Analyzing the minimum width for L p L^p L p approximation of L p L^p L p functions from [ 0 , 1 ] d [0,1]^d [ 0 , 1 ] d to R d y \mathbb R^{d_y} R d y using ReLU-like activation functions result The minimum width for L p L^p L p approximation on a compact domain is exactly max{d_x, d_y, 2} for ReLU-like activation functions The McCool group, denoted P Σ n PΣ_n P Σ n , is the group of pure symmetric automorphisms of a free group of rank n n n . The cohomology algebra H ∗ ( P Σ n , Q ) H^*(PΣ_n, \mathbb{Q}) H ∗ ( P Σ n , Q ) was determined by Jensen, McCammond and Meier. We prove that H ∗ ( P Σ n , Q ) H^*(PΣ_n, \mathbb{Q}) H ∗ ( P Σ n , Q ) is a non-Koszul algebra for n ≥ 4 n \geq 4 n ≥ 4 , which answers a question of Cohen and Pr…
The main theorem describes the behaviour of the stable cohomotopy invariant defined in the first article (joint with M. Furuta) in this series of two under the operation of taking connected sums of four-manifolds: The invariant of a connected sum is the smash product (in the sense of equivariant spectra) of the invaria…
SGD achieves near optimal convergence rate in smooth interpolation regime.
problem Optimization of smooth convex objectives with zero noise at optimum.
method Stochastic Gradient Descent (SGD) with large stepsize analysis.
result Last iterate of SGD achieves expected excess risk of O(1/T + σ* / √T) with optimal stepsize.
Unified approach to various energy conditions in spacetime geometry.
problem Synthetic quantification of energy conditions in spacetime.
method Introducing entropic timelike curvature dimension condition with variable Ricci curvature bounds.
result Unified approach to various energy conditions including strong, weak, and null energy conditions.
Optimal control in changing systems without strong convexity assumptions.
problem Adversarial changes in convex costs for unknown linear systems.
method Non-convex lower confidence bounds and computationally-efficient regret minimization.
result Achieves T \smash{\sqrt{T}} T -regret rate, optimal compared to best stabilizing controller. Stochastic linear bandits are a natural and well-studied model for structured exploration/exploitation problems and are widely used in applications such as online marketing and recommendation. One of the main challenges faced by practitioners hoping to apply existing algorithms is that usually the feedback is randomly …
New method reduces ensemble size for linear bandits, achieving near optimal regret.
problem Achieving near optimal regret in linear bandits with limited ensemble size.
method Ensemble sampling with a size of order d log T d \log T d log T for a d d d -dimensional stochastic linear bandit. result Regret is at most ( d log T ) 5 / 2 T (d \log T)^{5/2} \sqrt{T} ( d log T ) 5/2 T , improving over linear scaling with T T T . New method calibrates heterogeneous treatment effect models.
problem Difficulty in estimating and calibrating heterogeneous treatment effects.
method Defined and proposed a robust estimator for HTE calibration, based on doubly robust treatment effect estimators.
result Proposed method evaluates calibration of learned HTE models, addressing overfitting and high-dimensionality.
The paper extends a theorem to Lie-Rinehart algebras and provides new decompositions of universal enveloping algebras.
problem Understanding universal enveloping algebras of Lie-Rinehart algebras.
method Extending a theorem to left Hopf algebroids and applying it to universal enveloping algebras of Lie-Rinehart algebras.
result Provides a crossed product decomposition of universal enveloping algebras for curved and flat connections.
Study selective classification with limited feedback in online learning.
problem Resource-limited and safety-critical domains where feedback is only received on abstentions.
method Versioning-based schemes for minimizing mistakes and abstentions.
result Constructed schemes that make few mistakes and minimal excess abstentions.
New algorithm for minimizing regret in adversarial dueling bandits.
problem Minimizing regret in dueling bandits with adversarial feedback.
method Introduced an algorithm with T T T -round regret of i l d e O ( K 1 / 3 T 2 / 3 ) ilde{O}(K^{1/3}T^{2/3}) i l d e O ( K 1/3 T 2/3 ) . result Algorithm achieves Ω ( K 1 / 3 T 2 / 3 ) Ω(K^{1/3}T^{2/3}) Ω ( K 1/3 T 2/3 ) regret lower bound. Transformers can interpolate finite input sequences exactly.
problem Interpolating finite input sequences of arbitrary lengths.
method Constructing a transformer with alternating feed-forward and self-attention layers, and low-rank parameter matrices.
result Exact interpolation of datasets of finite input sequences in R^d with corresponding output sequences of smaller or equal length.
Defines a bundle map for currents on manifolds using higher covariant derivatives.
problem Defining a bundle map for currents on manifolds.
method Using higher covariant derivatives on a manifold equipped with a torsion-free connection.
result The bundle of generalized Weyl algebras and its properties.
New algorithms improve SGD convergence and reduce variance for over-parameterized models.
problem Slower convergence in non-interpolation settings for SGD variants.
method Proposed AdaSPS and AdaSLS with variance reduction for robust convergence.
result Achieves faster convergence rates and robustness in non-interpolation settings.
Stochastic Gradient Descent can overfit after just a few passes, contrary to initial expectations.
problem Understanding the out-of-sample performance of multi-pass SGD in stochastic convex optimization.
method Analysis of multi-pass SGD in the stochastic convex optimization model.
result Multi-pass SGD can lead to significant overfitting after just a few passes, contrary to initial expectations.
Big data sets must be carefully partitioned into statistically similar data subsets that can be used as representative samples for big data analysis tasks. In this paper, we propose the random sample partition (RSP) data model to represent a big data set as a set of non-overlapping data subsets, called RSP data blocks,…
A new method for handling imbalanced big data using ensembles and smart data.
problem Imbalanced data distribution in big data scenarios.
method Smart Data driven Decision Trees Ensemble (SD_DeTE) methodology.
result SD_DeTE outperforms Random Forest in handling imbalanced binary classification problems in big data.
Prevents sensitive data generation in diffusion models using labeled and unlabeled data.
problem Generating sensitive data in diffusion models using unlabeled data.
method Positive-Unlabeled Diffusion Models, approximating ELBO with labeled and unlabeled data.
result Prevents the generation of sensitive data without compromising image quality.
Study reveals Data Shapley's inconsistent performance in data selection tasks.
problem Inconsistency of Data Shapley's performance in data selection across different settings.
method Hypothesis testing framework and identification of utility functions.
result Data Shapley's performance is no better than random selection without specific constraints.
PRRO generates synthetic tabular data that improves SL performance and class distribution.
problem Low SL utility of synthetic data due to class imbalance and overlooked data relationships.
method Data pruning and column reordering to optimize SL utility.
result Synthetic data generated with PRRO enhances predictive performance and class distribution.
Defines data science as a natural ecosystem with challenges and missions.
problem Challenges and missions in data science due to 5D complexities and data life cycle phases.
method Systemic and data-centric view of data science as a fusion of data universe and its challenges, formalizing a general-purpose architecture.
result Essential data science as a natural ecosystem integrating specific disciplines and high-impact applications.
Synthetic data enhances analytics but requires careful volume management.
problem Accuracy of statistical methods on synthetic data vs. raw data.
method Synthetic Data Generation for Analytics framework using tabular diffusion models.
result Error rate decreases with more synthetic data but may stabilize or increase.
This paper introduces C-DSL to improve data mining outcomes by considering context.
problem Data collection ambiguities, data imbalance, hidden biases, lack of domain info, and data incompleteness.
method Developed Context-Driven Data Science Lifecycle (C-DSL) to address data quality issues.
result Tangible improvements to data mining outcomes were achieved through C-DSL.
Proposes using probabilistic models for privacy-preserving synthetic data.
problem Designing high-quality synthetic data for privacy preservation.
method Formulate the problem through probabilistic modelling, choosing a model for the data.
result Statistical discoveries can be reliably reproduced from synthetic data.
New test ensures quality of shared data in machine learning.
problem Ensuring quality of external data in machine learning tasks.
method Distribution-free two-sample testing procedures grounded in conformal outlier detection.
result Identifies valuable external data agents for model personalization.
Paper creates fair synthetic data ensuring equal predictions across sensitive attributes.
problem Ensuring fair predictions across sensitive attributes in synthetic data.
method Equalizing target probability distributions across sensitive attributes in synthetic data generation.
result Synthetic data provides strong fair predictions, equal across all thresholds.
DPA preserves data distribution in reduced dimensions.
problem Loss of data distribution in dimension reduction.
method DPA combines encoder and decoder to match data distribution.
result DPA successfully reconstructs data distribution.
Efficient synthetic data generation improves model performance on tabular data.
problem Improving model robustness and performance with scarce or low-quality data.
method Hardness characterization to identify high-value training points, generating synthetic data only from these points.
result Synthetic data generated from hardest points outperforms non-targeted methods on tabular datasets.
For most problems in science and engineering we can obtain data sets that describe the observed system from various perspectives and record the behavior of its individual components. Heterogeneous data sets can be collectively mined by data fusion. Fusion can focus on a specific target relation and exploit directly ass…
DAERNN models censored data using neural networks with data augmentation.
problem Handling censored data in expectile regression.
method Data augmentation based Expectile Regression Neural Networks (ERNNs).
result DAERNN outperforms existing censored ERNNs methods and achieves comparable predictive performance to fully observed data.