Adapts Thompson Sampling for contextual bandits with limited context.
problem Online problems in clinical trials, recommender systems, and attention modeling.
method Adapts Thompson Sampling to a restricted context setting.
result Empirical advantages of proposed algorithms on real-life datasets.
Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.
problem Fine-tuning harms in-context learning, reducing zero-shot performance on unseen tasks.
method Theoretical analysis of linear attention models, identifying conditions for degraded few-shot performance.
result Restricting updates to the value matrix improves zero-shot performance while preserving in-context learning.
Log-linear models are the popular workhorses of analyzing contingency tables. A log-linear parameterization of an interaction model can be more expressive than a direct parameterization based on probabilities, leading to a powerful way of defining restrictions derived from marginal, conditional and context-specific ind…
We generalize the notion of involutivity to systems of differential equations of different orders and show that the classical results due to Guillemin and Quillen relating involutivity, restrictions, characteristics and characteristicity, known for first order systems, extend to the general context, though in a modifie…
Three versions of the Freiheitssatz are proved in the context of one-relator quotients of limit groups, where the latter are equipped with 1-acylindrical splittings over cyclic subgroups. These are natural extensions of previously published corresponding statements for one-relator quotients of orientable surface groups…
New RBM method for missing data inference, comparing performance to existing methods.
problem Missing data inference and perception-distortion trade-off.
method Linearization of RBM effective energy function for missing data.
result Proposed method outperforms existing reconstruction procedures in missing data inference.
MCPCA analyzes shared factors across multiple data contexts.
problem No tools to recover shared factors across multiple contexts.
method Developed a theoretical and algorithmic framework (MCPCA).
result Reveals shared axes of variation across subsets of contexts.
Pooling data across users improves prediction of context occurrences in mobile health interventions.
problem Diffusing treatment delivery over times when a user is in a desired context.
method Investigated several methods to pool data across users to overcome individual-level data limitations.
result Pooling data lowers overall error rate compared to personalized and batch approaches.
Unified framework for generalized sparsity and RIP analysis.
problem Analyzing inverse problems with sparsity models.
method Proposed generalized notions of sparsity and a unified RIP framework.
result Extends RIP analysis to broader contexts including tensor products.
In this paper, we construct smooth forward Ricci flow evolutions of singular initial metrics resulting from rotationally symmetric neckpinches on S^(n+1), without performing an intervening surgery. In the restrictive context of rotational symmetry, this construction gives evidence in favor of Perelman's hope for a "can…
Study Higgs bundles on smooth projective varieties and their restrictions to curves.
problem Interplay between Higgs bundles on smooth projective varieties and their restrictions to curves.
method Investigate the restriction map of Higgs bundles and study branes in moduli spaces.
result Interconnectedness of Higgs bundles and branes on smooth projective varieties and their restrictions.
The abstract discusses combining risk measures without restrictions.
problem Developing a theory for combinations of risk measures under no restrictions.
method Developing and discussing results regarding preservation of properties and acceptance sets for combinations of risk measures.
result Representation of resulting risk measures from the properties of alternative functionals and combination functions.
Let L 2 L^2 L 2 be the Lebesgue space of square-integrable functions on the unit circle. We show that the injectivity problem for Toeplitz operators is linked to the existence of geodesics in the Grassmann manifold of L 2 L^2 L 2 . We also investigate this connection in the context of restricted Grassmann manifolds associated to $p…
Continuum transformers learn operators in context via gradient descent.
problem Generalizing transformers to handle infinite-dimensional inputs for in-context learning.
method Gradient descent in an operator RKHS, leveraging generalized representer theorems and gradient flows.
result Operator learned in context is Bayes Optimal Predictor in infinite depth limit.
We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations o…
Improves data recovery with optimized measurements and generalized sparsity models.
problem Data recovery with optimized measurements and generalized sparsity models.
method Optimizing over families of Banach spaces, investigating preservation of difference of sparse vectors, extending RIP to group structured measurements, and extending Fourier measurement concepts to infinite dimensions.
result Optimal scaling of number of measurements for group structured measurements and improved RIP in infinite dimensions.
New analysis proves sketching operators' RIP guarantees for mixture models without importance sampling.
problem Proving sketching operators' Restricted Isometry Property (RIP) for mixture models without assuming importance sampling.
method Proposed alternative analysis based on new deterministic bounds and concentration inequalities.
result Theoretical guarantees for sketching operators without importance sampling.
Generative Distributionally Robust Optimization (GDRO) improves model compatibility and adversarial structure in DRO.
problem Trade-off between model compatibility and adversarial structure in existing DRO methods.
method GDRO accepts any sampleable conditional generator and restricts worst-case laws to a chosen family, using sampler-Sinkhorn pairing.
result Reduces inventory regret by 60% and navigation collisions by 50% relative to nominal decisions.
Method predicts RMST from censored data using pseudo-observations and super learner.
problem Estimating RMST from right-censored data.
method Ensemble algorithm combining pseudo-observations and super learner.
result Method performs well in simulations and real data applications.
Improves medical note processing by training model on related concepts and global context.
problem Scarce and imbalanced labeled training data limits generalizability of automated abbreviation disambiguation models.
method Data augmentation using related medical concepts and global context information within medical notes.
result Model accuracy improved by almost 14% on CASI dataset and 4% on i2b2 dataset.
New algorithm speeds up SVAR inference for large datasets.
problem Inference in sign-identified SVARs for big data.
method Elliptical slice within Gibbs sampler for computational efficiency.
result Algorithm delivers posterior distribution and is well-defined.
Study expands harmonic almost contact metric structures classification.
problem Characterizing harmonic almost contact metric structures.
method Using intrinsic torsion and restrictions on structure types, the study generalizes previous work.
result Conditions relating harmonicity and almost contact metric structures are established.
EDRBO optimizes Bayesian optimization with continuous contexts using ensemble models and robust methods.
problem Bayesian optimization with unknown and continuous contextual distributions leads to suboptimal results.
method EDRBO uses ensemble surrogate models and Wasserstein ball ambiguity sets to handle uncertainty and maintain computational tractability.
result EDRBO achieves sublinear cumulative regret guarantees of order O ( γ T T ) \mathcal{O}(γ_T \sqrt{T}) O ( γ T T ) . A new algorithm uses IVs to learn optimal policies from observational data.
problem Learning optimal policies from unobserved variable confounded data.
method IV-aided Value Iteration (IVVI) algorithm based on conditional moment restrictions.
result First provably efficient algorithm for instrument-aided offline RL.
New classifiers account for context-specific independences.
problem Restrictions in generative models for classification.
method Staged tree classifiers that account for context-specific independences.
result Staged tree classifiers achieve competitive classification accuracy.
Hierarchical beta process has found interesting applications in recent years. In this paper we present a modified hierarchical beta process prior with applications to hierarchical modeling of multiple data sources. The novel use of the prior over a hierarchical factor model allows factors to be shared across different …
DaConA improves recommendation accuracy with auxiliary data by adapting to different data contexts.
problem Improving recommendation accuracy with auxiliary data considering different data contexts.
method Data context adaptation layer, latent interaction vector, latent independence vector, non-linear function.
result DaConA achieves state-of-the-art accuracy on real-world datasets.
Generative Kernel PCA explores latent spaces for data interpretation and novelty detection.
problem Exploring latent spaces of datasets for better data interpretation.
method Generative Kernel PCA using hidden and visible units similar to Restricted Boltzmann Machines.
result Gradually moving in the latent space allows for interpretation of components and detection of novel patterns.
New GL-GP models learn covariance respecting domain geometry.
problem Suboptimal results from nonparametric regression on restricted domains.
method Graph Laplacian based Gaussian Processes (GL-GPs) with Nyström extension.
result Performance gains in various applications.
The main object of the present paper is to study the geometric properties of a generalized Roter type semi-Riemannian manifold, which arose in the way of generalization to find the form of the Riemann-Christoffel curvature tensor R R R . Again for a particular curvature restriction on R R R and the Ricci tensor S S S there ar…
Looped Transformers improve robustness and expressivity in in-context learning for diverse tasks.
problem Improving robustness and expressivity in in-context learning for diverse tasks.
method Study in-context linear regression with diverse tasks, focusing on depth and looping.
result Looped Transformers exhibit similar expressive power and are provably robust under mild assumptions.
Deep neural network improves DNA methylation data analysis.
problem Analyzing highly dimensional DNA methylation data with bounded support.
method Designing a deep neural network composed of stacked binary restricted Boltzmann machines.
result Deep features learned by the neural network perform best in cluster analysis of breast cancer DNA methylation data.
New method uses kernel Stein discrepancy for measure transport without strict continuity constraints.
problem Minimizing Kullback-Leibler divergence for posterior approximation.
method Proposes minimizing kernel Stein discrepancy instead of Kullback-Leibler divergence.
result Demonstrates consistency and competitiveness of the new method.
This paper addresses missing covariates in stochastic linear bandits, providing a high-probability regret bound.
problem Effect of missing covariates on regret in stochastic linear bandit algorithms.
method Proposes an algorithm that provides a high-probability upper bound on regret in terms of covariate sampling probabilities.
result Regret degrades due to missingness by at most ζ m i n 2 ζ_{min}^2 ζ min 2 , where ζ m i n ζ_{min} ζ min is the minimum probability of observing covariates. Due to spectral obstructions, a scattering theory in the Lax-Phillips sense for the wave equation for differential p-forms on H^{n+1} cannot be developed. As a consequence, Huygens' principle for the wave equation in this context does not hold. If we restrict the class of forms and we consider the case of coclosed p-fo…
Proposes ContSup to boost local learning by supplying context between isolated modules.
problem Local learning's performance degrades with more isolated modules.
method Theoretical analysis and ContSup scheme to supply context between modules.
result Significant performance improvement with minimal overhead.
Recently the authors have explored new concepts of plurisubharmonicity and pseudoconvexity, with much of the attendant analysis, in the context of calibrated manifolds. Here a much broader extension is made. This development covers a wide variety of geometric situations, including, for example, Lagrangian plurisubhamon…
Study arbitrage in financial markets with trading restrictions.
problem Arbitrage in financial markets with trading constraints.
method Portfolio optimization problems and discrete-time setup.
result Solvability of portfolio optimization problems equivalent to absence of first kind arbitrage.
Paper presents a method for estimating Hawkes process parameters.
problem Estimating parameters of Hawkes processes with self-excitation or inhibition.
method Maximum likelihood estimation for Hawkes processes with self-excitation or inhibition.
result The proposed estimator provides more accurate estimations in the inhibition context.
New RL algorithms adapt to time limits, improving task performance.
problem Fixed RL behaviors cannot adapt to different time restrictions.
method Introduced two algorithms for time adaptive RL: Independent Gamma-Ensemble and n-Step Ensemble.
result Zero-shot adaptation between different time restrictions.
Paper proposes dp-VAE for preserving spatial context in gene expression data.
problem Inaccessibility of spatial context in single-cell gene expression data.
method Generic representation learning and transfer learning framework with a distance-preserving regularizer.
result dp-VAE effectively reconstructs and imputes spatial context from gene expression data.
The paper extends a learning heuristic to high-dimensional contexts, reducing the risk of unusual actions.
problem Sequential learning problems in high dimensions, especially in dynamic pricing and auctions.
method Introducing a conservative ε t ε_t ε t -greedy rule that limits the adoption of new actions to a focused set of promising actions. result Reasonable bounds for cumulative regret and improved regret bound for conservative version compared to non-conservative.
New tools for constructing disintegrations and studying their modes.
problem Difficulty in constructing disintegrations and understanding their modes.
method Developed comprehensive mathematical tools for constructing disintegrations and analyzing their modes.
result Disagreement between restricted density and disintegration density in certain cases.
Paper presents a new Pohozaev-Schoen identity for non-compact manifolds.
problem Analyzing geometric problems on asymptotically Euclidean manifolds.
method Develops a generalized Pohozaev-Schoen identity for these manifolds.
result Shows applications including rigidity results for Ricci-solitons and Codazzi-solitons.
Paper constructs GCM spheres for Kerr family, removing symmetry restriction.
problem Establishing full nonlinear stability of Kerr family for perturbations.
method Introduction and construction of GCM hypersurfaces, removing symmetry restrictions.
result GCM spheres can be constructed for Kerr family without symmetry restrictions.
The study explores ends in coarse homotopy of proper geodesic spaces.
problem Understanding ends in coarse homotopy of proper geodesic spaces.
method Recontextualizing ends as a functor and proving properties of coarse path components.
result Existence of a natural surjection from coarse path components to ends, not always an injection.
New theory allows ICA without assuming non-Gaussian sources.
problem Traditional ICA struggles with Gaussian sources.
method Developed identifiability theory based on second-order statistics and sparsity.
result Identifiability theory and estimation methods validated experimentally.
New algorithms for private generalized linear contextual bandits.
problem Private estimation and optimization for generalized linear models under differential privacy.
method Developed algorithms for stochastic and adversarial contexts under shuffle and joint differential privacy.
result Achieved private regret bounds for generalized linear models, differing from non-private rates by factors of d / ε \sqrt{d/\varepsilon} d / ε and d / ε \sqrt{d/\varepsilon} d / ε respectively.