A new framework reduces inconsistencies in chaotic surrogate modeling.
problem Consistency issues between probabilistic objectives and dynamical system dynamics.
method KAFFEE (Kalman-Aware Framework For Ergodic Emulation), a differentiable extended Kalman filter.
result KAFFEE mitigates the dynamic-probabilistic consistency gap, improving reconstruction and predictive scores.
This paper describes a method for clustering data that are spread out over large regions and which dimensions are on different scales of measurement. Such an algorithm was developed to implement a robotics application consisting in sorting and storing objects in an unsupervised way. The toy dataset used to validate suc…
Paper establishes a universal growth rate for smooth surrogate losses in classification.
problem Analyzing growth rates of consistency bounds for various surrogate losses.
method Proves square-root growth rate for smooth margin-based losses; extends to multi-class classification.
result Demonstrates a universal square-root growth rate for smooth comp-sum and constrained losses.
The paper derives upper bounds on eigenvalues of Laplace-Beltrami operator on hyperbolic surfaces.
problem Finding upper bounds on eigenvalues of Laplace-Beltrami operator on hyperbolic surfaces.
method Using spectral decompositions and consistency conditions derived from quadruple overlap integrals in terms of triple overlap integrals.
result Derives upper bounds on eigenvalues, nearly saturated by the Bolza surface.
As a testament to their success, the theory of random forests has long been outpaced by their application in practice. In this paper, we take a step towards narrowing this gap by providing a consistency result for online random forests.
Directed graphs in tournaments can link or knot in various ways.
problem Understanding intrinsic linking and knotting in directed graphs, specifically tournaments.
method Analyzing the minimum number of vertices required for intrinsic linking or knotting properties in tournaments.
result Bounds on the minimum number of vertices required for various intrinsic linking or knotting properties in tournaments.
Theoretical study explains why randomization improves adversarial robustness.
problem Lack of theoretical arguments for randomization techniques in adversarial robustness.
method Theoretical analysis of randomization techniques for adversarial robustness.
result New theoretical upper bound on adversarial generalization gap.
Convex clustering can only learn convex clusters, with significant gaps between clusters.
problem Understanding the limitations and capabilities of convex clustering.
method Analyzing convex clustering solutions, proving properties, and characterizing clusters.
result Convex clustering can only learn convex clusters with significant gaps between clusters.
This note fills the gap in market-consistent valuation of lifelong health insurance products.
problem Market-consistent valuation of lifelong health insurance products is not well-addressed.
method Constructs a valuation portfolio to separate Best Estimate into policy data and financial instrument prices.
result The Best Estimate valuation is not uniquely determined by prevailing term structures and requires a stochastic model.
Deep learning models predict generalization gaps without specific task or architecture.
problem Predicting when deep learning works across different tasks and architectures.
method Created a dataset of 13,500 neural networks trained on various spiral datasets and parameters. Used this dataset to train predictors for generalization gaps.
result DNNs and RNNs outperform linear models in predicting generalization gaps, with RNNs achieving R2=0.584. This paper improves multi-label ranking by reweighting univariate losses, enhancing consistency and performance.
problem Improving multi-label ranking performance while maintaining consistency.
method Systematic study of consistency and generalization error bounds for learning algorithms, proposing a reweighted univariate loss.
result Inconsistent pairwise losses can lead to better performance than consistent univariate losses in practice.
VAEs improve representation learning by inverting the data-generating process through self-consistency.
problem VAEs struggle to invert the data-generating process, yet often succeed in representation learning.
method Studied VAEs in the limit of near-deterministic decoders, proving self-consistency and showing ELBO convergence to a regularized log-likelihood.
result VAEs can perform independent mechanism analysis (IMA), recovering true latent factors under specific conditions.
Theoretical analysis of MCR for improving imputation quality in partially observed data.
problem Improving model generalization in partially observed settings.
method Theoretical analysis of Measure Consistency Regularization (MCR) for neural network distance.
result MCR's generalization advantage is not always guaranteed and can be monitored through a duality gap.
The paper constructs noncompact hyperbolic surfaces with uniform spectral gaps using random graph models.
problem Building noncompact hyperbolic surfaces with uniform spectral gaps.
method Introduced a random graph model Fχ,n to construct expanding families of graphs, then applied these families to create hyperbolic surfaces. result Explicitly constructed an expanding family of graphs in the critical regime, leading to a sequence of complete, noncompact hyperbolic surfaces with uniformly positive spectral gaps.
Prediction markets and crypto options show persistent pricing gaps.
problem Comparing prediction markets and crypto options for identical payoffs.
method Comparing Polymarket Yes prices with Binance call option prices.
result Mean pricing gap of 5.6 percentage points across 214 hourly observations.
The classical Three Gap Theorem asserts that for a natural number n and a real number p, there are at most three distinct distances between consecutive elements in the subset of [0,1) consisting of the reductions modulo 1 of the first n multiples of p. Regarding it as a statement about rotations of the circle, we find …
Estimates generalization gap for overparameterized models using Langevin approximation.
problem Estimating the difference between training and generalization performance in overparameterized models.
method Functional variance and Langevin approximation of functional variance.
result Demonstrates efficient estimation of generalization gaps for overparameterized models.
New method for conformal prediction under Markovian data reduces coverage gap.
problem Reducing coverage gap in conformal prediction for Markovian data.
method Split Conformal Prediction method adapted to Markovian data, with K-split CP for improved performance.
result Coverage gap typically scales as √(t_mix * ln(n) / n) for general Markov chains, and can be reduced to t_mix / (n * ln(n)) with K-split CP.
Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases, introduced due to tractability considerations, has largely remained under-appreci…
Survey examines challenges and solutions in sim-to-real transfer for robotics.
problem Challenges in transferring robotic systems from simulation to real-world environments.
method Leveraging techniques like domain randomization, real-to-sim transfer, state and action abstractions, and sim-real co-training.
result Promising results in closing the reality gap across various robotic domains.
Machine learning predicts band gaps for large organic crystals.
problem Predicting band gaps for complex organic crystal structures.
method Released a dataset of 12,500 crystal structures and their band gaps. Trained two state-of-the-art models to achieve a mean absolute error of 0.388 eV.
result Trained models predict band gaps with 13% error for an average gap of 3.05 eV.
Optimal strategy found for identifying best arm in bandits with small gap.
problem Best arm identification in two-armed bandits with a fixed budget and small gap.
method Neyman allocation rule augmented with inverse probability weighting.
result Proposed strategy is asymptotically optimal when gap is small.
A popular approach to semi-supervised learning proceeds by endowing the input data with a graph structure in order to extract geometric information and incorporate it into a Bayesian framework. We introduce new theory that gives appropriate scalings of graph parameters that provably lead to a well-defined limiting post…
Study best arm identification with contextual info, achieving optimal misidentification probability.
problem Identify the best treatment arm with minimal misidentification probability in a small gap scenario.
method Developed RS-AIPW strategy that matches lower bound of misidentification probability in the small-gap regime.
result RS-AIPW strategy is asymptotically optimal for best arm identification.
The study finds that firm membership in flagship indices and TCFD endorsement are strong predictors of a wider Disclosure-Performance Gap.
problem The Aggregate Confusion hypothesis and the measurement of greenwashing in environmental disclosures.
method The study uses a Disclosure-Performance Gap (DPG) model to measure the divergence between voluntary environmental disclosures and realised emissions performance for 200 large European firms. The model selection process involved multiple stages and robust standard errors.
result Firm membership in flagship indices and TCFD endorsement are strong predictors of a wider gap, while renewable energy use and environmental capital expenditure significantly narrow the gap.
Method constrains spectral gaps of hyperbolic spin surfaces using identities and semidefinite programming.
problem Bounding Laplacian and Dirac spectra of hyperbolic spin manifolds and orbifolds.
method Infinite family of spectral identities, semidefinite programming, and Selberg trace formula.
result Upper bounds on spectral gaps nearly saturated by specific orbifolds.
The study uses Random Matrix Theory to identify structural changes in stock markets during shocks.
problem Understanding structural changes in stock markets during exogenous shocks.
method Random Matrix Theory and complexity gap analysis.
result The complexity gap collapses during shocks, indicating strong synchronization, and widens before shocks, signaling a rich structure.
Study quantifies performance gap between tensor and matrix-based approaches in nested matrix-tensor model.
problem Estimating a planted signal in a nested matrix-tensor model.
method Comparing tensor-based and matrix-based approaches for best rank-one approximation of tensor data.
result Derives precise algorithmic threshold for the unfolding approach and shows BBP-type transition behavior.
DGKIP extends KIP for dataset distillation without bi-level optimization.
problem Efficiently distill datasets for various loss functions.
method Leverages duality theory to avoid bi-level optimization.
result DGKIP supports a wider range of loss functions.
The paper validates a classifier for identifying intraday regime shifts in MNQ futures.
problem Developing reliable trading signals from intraday regime shifts in MNQ futures.
method Constructed a composite day-classification system using three observable conditions.
result Classifier-positive days exhibit distinct intraday behavior but fail to generate profitable trading signals.
Transitive consistency is an intrinsic property for collections of linear invertible transformations between Euclidean coordinate frames. In practice, when the transformations are estimated from data, this property is lacking. This work addresses the problem of synchronizing transformations that are not transitively co…
New method improves consistency in preference learning for neural networks.
problem Inconsistent surrogate losses in preference learning for neural networks.
method Formulated a margin-shifted ranking framework and introduced Structure-Aware H-consistency. result Proved superior consistency guarantees for capacity-bounded models using heavy-tailed surrogates.
Foundation models improve wage gap decomposition by capturing omitted career history factors.
problem Estimating wage disparities using incomplete career history data.
method Fine-tuning foundation models to mitigate omitted variable bias and estimate wage gaps.
result Foundation models can decompose gender wage gaps more accurately than traditional econometric methods.
Paper tackles fast convergence for non-convex strongly-concave min-max problems.
problem Non-convex strongly-concave min-max problems in deep learning.
method Proximal stage-based method with PL condition for faster convergence.
result Established fast convergence in primal objective gap and duality gap.
MaxMatch improves SSL with worst-case consistency for better generalization.
problem Efficiently supervised learning with unlabeled data.
method Worst-case consistency regularization for SSL, providing a bound and an algorithm.
result The proposed method converges to a stationary point and improves generalization.
Improves VAE training by refining variational parameters with BSVI.
problem Amortized inference in VAEs leads to suboptimal variational parameters and the amortization gap.
method Proposes BSVI, a refinement procedure using SVI's importance weights.
result Training VAEs with BSVI yields improved performance compared to SVI.
This paper revisits the distribution gap between clean and augmented data in deep learning.
problem The distribution gap between clean and augmented data in deep learning models.
method Analytical perspective using empirical risk and generalization error, highlighting data augmentation as regularization.
result Data augmentation significantly reduces generalization error but slightly increases empirical risk.
New metric explains neural network performance, simplifying generalization error calculation.
problem Precise characterization of neural network generalization error.
method Introducing Representation Gap, linking to intrinsic dimension and equivariant diffusion models.
result Asymptotic equivalent of Representation Gap is governed by intrinsic dimension, easy to estimate.
Study examines consistent graph recovery from partial network data.
problem Consistent graph recovery from partially observed diffusion networks.
method Developed estimators for combination matrix under partial observability.
result Node degrees' statistical concentration enables consistent graph learning.
The paper explores how simplicity leads to better out-of-distribution generalization in models.
problem Understanding the theoretical principles behind out-of-distribution (OOD) generalization in modern models.
method Examining diffusion models in image generation to analyze compositional generalization abilities and develop a theoretical framework for simplicity-based OOD generalization.
result The true, generalizable model corresponds to the simplest among consistent models, and this simplicity can be quantified and used to establish sample complexity guarantees.
High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subs…
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that softmax consistent action values correspond to optimal entropy regularized policy pro…
Paper improves imitation learning from observations by minimizing inverse dynamics disagreement.
problem Challenges in Learning from Observations (LfO) due to incomplete expert guidance.
method IDDM method that minimizes the disagreement between inverse dynamics models of the imitator and expert.
result Empirical results show consistent improvements over other LfO methods.
Modified relative universality for unbiasedness and consistency in dimension reduction.
problem Gap in proof of unbiasedness and Fisher consistency in relative universality.
method Modified definition of relative universality using ǫ-measurability.
result Established unbiasedness and Fisher consistency rigorously.
GAP learns node representations by attending to different parts of its neighborhood.
problem Context-free learning of node representations in graph representation learning.
method Graph Neighborhood Attentive Pooling (GAP) using attentive pooling networks.
result GAP outperforms 10 state-of-the-art methods on link prediction and clustering tasks.
Theoretical analysis of cross-entropy loss functions and their robustness.
problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First H-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses. A new framework integrates classification and regression tasks in multi-task learning.
problem Jointly solving classification and regression tasks in multi-task scenarios.
method Two-Stage Learning-to-Defer (L2D) framework with a unified deferral mechanism.
result Unified deferral mechanism ensures convergence to the Bayes-optimal rejector.
The study proves unique and isolated properties of Einstein 5-manifolds via gap theorems in 4 dimensions.
problem Understanding the structure and regularity of Einstein 5-manifolds.
method Analysis of tangent cones, gap theorems for 4-dimensional orbifolds, and careful metric analysis.
result Noncollapsed limits of Einstein 5-manifolds have unique and isolated tangent cones.