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.
Efficient algorithm for learning from indirect feedback in complex decision-making scenarios.
problem Learning from indirect feedback in realistic scenarios with personalized mechanisms.
method IGW algorithm for policy optimization, extending reward-estimator construction from single-step to multi-step.
result Achieves sublinear regret guarantee for contextual episodic MDPs with personalized feedback.
New strategy optimally identifies best arm in unknown variance Gaussian bandits.
problem Identifying the best arm in two-armed Gaussian bandits with unknown variances.
method Proposes a Neyman Allocation (NA)-Augmented Inverse Probability weighting (AIPW) strategy to estimate variances and draw arms adaptively.
result Demonstrates asymptotic optimality of the proposed strategy in the small-gap regime.
New algorithms improve efficiency in learning from personalized rewards.
problem Learning from personalized rewards in recommendation systems.
method Developed provably efficient algorithms with sublinear regret for context-dependent feedback.
result Introduced a Lipschitz reward estimator that improves generalization performance.
Proposes stabilized weights for causal inference using isotonic calibration.
problem Stability and bias issues in inverse propensity weighting.
method Post-hoc isotonic calibration of inverse propensity weights.
result Improves performance of doubly robust estimators of average treatment effect.
This work bridges federated learning and contextual bandits, enhancing FL's utility.
problem Limited use of federated learning in contextual bandits despite its potential.
method Proposes FedIGW, a novel federated contextual bandits design that leverages regression-based algorithms and integrates various FL components.
result FedIGW better harnesses FL innovations and provides flexible, modular, and seamless integration of FL elements.
Unified framework for critical scaling of inverse temperature in self-attention.
problem Conflicting inverse-temperature laws for long-context self-attention.
method Counting gaps and defining an upper-tail accumulation scale.
result Critical inverse-temperature scale determined by gap-counting function.
Unified framework for causal inference under sample selection.
problem Causal inference under sample selection with treatment and outcome non-randomness.
method ForestRiesz estimator, Riesz representation framework.
result ForestRiesz estimator yields more stable treatment effect estimates than conventional double machine learning approaches.
R-Learning uses inverse-variance weights to estimate treatment effects more accurately.
problem Estimating heterogeneous treatment effects (CATEs) with stable and accurate methods.
method R-Learning with inverse-variance weights (IVWs) for pseudo-outcome regression.
result IVWs improve the stability and accuracy of CATE estimation.
The paper addresses estimating long-term treatment effects with monotone missing data.
problem Estimating long-term treatment effects with missing data, especially monotone missing.
method The paper introduces the sequential missingness assumption for identification and proposes three novel estimation methods: inverse probability weighting, sequential regression imputation, and SeqMSM. It also introduces a balancing-enhanced approach, BalanceNet, to improve estimation accuracy.
result The proposed methods, including BalanceNet, effectively estimate long-term treatment effects with monotone missing data.
The paper proves lower bounds for Gaussian-weighted curvature integrals of self-shrinkers.
problem Proving lower bounds for Gaussian-weighted \(L^2\)-curvature integrals of self-shrinkers.
method Combining normal coordinate functions with weighted Poincaré inequalities and first-eigenvalue estimates.
result Explicit lower bounds in terms of entropy for closed self-shrinkers, leading to curvature gaps.
Improves deep learning performance on noisy datasets using inverse-variance weighting.
problem Heteroscedastic regression with varying noise levels.
method Batch Inverse-Variance (BIV) loss function for neural networks.
result Significantly improves network performance on noisy datasets compared to other methods.
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.
Develops algorithms for CCBs with non-linear costs, improving safety and performance.
problem Safety constraints in sequential decision making with non-linear arm costs.
method Innovative algorithms using Inverse Gap Weighting (IGW) and online regression oracle.
result Sub-linear regret bounds for C-SquareCB and first-order regret for C-FastCB.
New nonparametric estimators improve causal effect estimation.
problem Estimation of causal effects with selection bias.
method Undersmoothing of the highly adaptive lasso for estimating the weighting mechanism.
result Asymptotic efficiency and convergence to nonparametric efficiency bound.
This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervision, LfO is more practical in leveraging previously inapplicable resources (e.g. videos), yet more challenging…
In this article we consider the anisotropic Calderon problem and related inverse problems. The approach is based on limiting Carleman weights, introduced in Kenig-Sjoestrand-Uhlmann (Ann. of Math. 2007) in the Euclidean case. We characterize those Riemannian manifolds which admit limiting Carleman weights, and give a c…
Hierarchical clustering uses OWA operators to generalize linkage methods and avoid dendrogram inversions.
problem Avoiding unaesthetic inversions in hierarchical clustering dendrograms.
method OWA-based linkages combined with the Lance-Williams formula and conditions on weight generators.
result Conditions for weight generators to produce dendrograms without inversions.
Study inverse problems with measure samples, improving estimator calibration and recovery.
problem Inverse problems with unknown potentials observed through measure samples.
method Introduced convex empirical objectives and sharpened Fenchel--Young losses for finite-dimensional potential classes.
result High-probability parameter recovery bounds for inverse entropic unbalanced optimal transport and inverse JKO learning.
Hybrid regularization avoids double descent in random feature models.
problem Avoiding the double descent phenomenon in random feature models.
method Combines early stopping and weight decay, using GCV for hyperparameter selection.
result Hybrid method successfully avoids double descent and achieves comparable generalization.
In this paper we prove L∞ type gap theorems in Yang-Mills theory for complete four-dimensional manifolds with a weighted Poincaré inequality. We apply the theorems to a broad class of complete manifolds satisfying weighted Poincaré inequalities. In particular, we obtain a gap theorem on the Euclidean space wi…
A new topological gap theorem improves the systole of 3-manifolds with positive scalar curvature.
problem Improving the systole of 3-manifolds with positive scalar curvature.
method Weak inverse mean curvature flow.
result The systole of 3-manifolds is no greater than an improved constant c ≈ 5.44π.
Innovative game theory approach optimizes survival analysis metrics.
problem Survival analysis models trained with maximum likelihood do not directly optimize criteria like Brier score or Bernoulli log likelihood.
method Inverse-Weighted Survival Games: Construct objectives from re-weighted estimates featuring the other model, holding the latter fixed during training.
result Games optimize Brier score on simulations and real-world data.
Study shows refugee matching gains are robust to different evaluation methods.
problem Stability of refugee matching gains under various evaluation methods.
method Used multiple off-policy evaluation methods including IPW and AIPW.
result Impact estimates remain consistent in magnitude and statistically significant.
The original Broad Learning System (BLS) on new added nodes and its existing efficient implementation both assume the ridge parameter lambda -> 0 in the ridge inverse to approximate the generalized inverse, and compute the generalized inverse solution for the output weights. In this paper, we propose two ridge solution…
We study the inverse spectral problem for weighted projective spaces using wave-trace methods. We show that in many cases one can "hear" the weights of a weighted projective space.
This study develops a dynamic inverse optimization framework to recover hidden, time-varying preferences from observed allocation trajectories.
problem The gap between classical optimization theory and real-world practice, especially in the presence of drift and shocks.
method Dynamic inverse optimization framework using a drift-aware estimator grounded in convex analysis and online learning theory.
result Sharp static and dynamic regret bounds for the framework, demonstrating its responsiveness to gradual drift and sudden shocks.
A new method for covariate shift adaptation using nearest neighbors.
problem Mitigating distribution shift between source and target datasets.
method Directly work on unlabeled target data, labeled by nearest neighbors in source data.
result Optimal choice of k=1 simplifies hyper-parameter tuning and improves efficiency. Graph semi-supervised learning classifies points on manifold using variational autoencoders and GNN.
problem Classifying points on low-dimensional manifolds using limited labeled data.
method Model data as points on a manifold, approximate manifold with VAE, construct geometric graph, solve semi-supervised node classification with GNN.
result Generalization gap diminishes with graph size and training procedure, vanishing asymptotically.
Unified framework for Bayesian PDE-constrained inversion using physics-informed neural networks.
problem Incorporating prior distributions in function space into Bayesian PINN-based inversion.
method Functional-prior-based approaches (fpBPINN) to Bayesian PDE-constrained inversion using physics-informed neural networks (PINNs). Two complementary approaches: FPI-BPINN and fParVI-PINN.
result Accurate estimation of posterior distributions in seismic traveltime tomography and Darcy-flow permeability inversion.
Transformer learns context and regularization for ICL in inverse problems.
problem Learning context and effective regularization for transformer-based in-context learning (ICL) in inverse problems.
method Introduced a linear transformer to learn inverse mapping from contextual examples to weight vectors, addressing rank-deficient problems.
result Transformer implicitly learns a prior distribution and effective regularization strategy, outperforming traditional methods.
Efficient algorithm removes redundant nodes and obsolete samples in machine learning.
problem Pruning redundant nodes and removing obsolete training samples in machine learning.
method Deduced decremented learning algorithms from incremental learning algorithms, using inverse Cholesterol factor and unitary transformation.
result Proposed decremented learning algorithms efficiently prune redundant nodes and remove obsolete training samples.
Adversarial robustness improved by sparsity in network weights.
problem How sparsity affects adversarial robustness in neural networks.
method Theoretical proof and experimental validation of adversarial pruning methods.
result Weights sparsity improves adversarial robustness, especially through inheritance from smaller networks.
A new machine learning method for spatial regression.
problem Spatial/temporal regression with scattered data and arbitrary dimensions.
method Modified Planar Rotator (MPRS) method, a non-parametric model with distance-dependent interactions.
result MPRS predictions are competitive with standard interpolation methods and superior in handling rough and non-Gaussian data.
Gaussian process regression helps approximate Bayesian inverse problems efficiently.
problem Computational intractability of Bayesian posterior distributions in inverse problems.
method Gaussian process regression to build a surrogate model for the likelihood.
result Error between true and approximate posterior can be bounded by weighted L2-norm error between true and approximate likelihood. We prove inverse spectral results for differential operators on manifolds and orbifolds invariant under a torus action. These inverse spectral results involve the asymptotic equivariant spectrum, which is the spectrum itself together with "very large" weights of the torus action on eigenspaces. More precisely, we show …
Graph curvature measured by inverse resistance distance.
problem Defining and analyzing curvature in graphs.
method Defining curvature via inverse resistance distance and proving properties.
result Graphs with positive curvature have controlled diameter and spectral properties.
Proof of existence and uniqueness of weighted Voronoi-Delaunay on polyhedral surfaces.
problem Existence and uniqueness of weighted Voronoi-Delaunay on polyhedral surfaces.
method Construct an isotopic map instead of edge-flipping algorithm, generalizing Dyer et al's method.
result Strict proof of existence and uniqueness of weighted Voronoi-Delaunay on polyhedral surfaces.
The paper proves existence and growth estimates for inverse mean curvature flow and related p-Laplacian Green kernel decay.
problem Existence and growth estimates for inverse mean curvature flow.
method Proving new decay estimates for the Green kernel of the p-Laplacian. result Existence and optimal growth estimates for the weak inverse mean curvature flow.
Contextual bandit methods fail with deficient support data.
problem Learning from support-deficient data in contextual bandits.
method Three approaches to IPS-based learning: action space restriction, reward extrapolation, and policy space restriction.
result Systematic analysis and empirical evaluation of approaches to IPS-based learning.
New method improves causal effect estimation by addressing imbalance in training data.
problem Imbalance between treatment and control groups in training data.
method Combines distributionally robust optimization and weight regularization.
result Consistent improvements over existing methods in experiments.
Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or recommendations, that optimally improve the probability of the class label. In this work…
We give a family of monotone quantities along smooth solutions to the inverse curvature flows in Euclidean spaces. We also derive a related geometric inequality for closed hypersurfaces with positive k-th mean curvature.
Study of curve evolution in 2D space forms converging to a circle.
problem Understanding curve evolution in 2D space forms.
method Inverse curvature flow with normal speed defined by weighted inverse curvature and support function.
result Solutions exist for all time and converge exponentially to a standard round geodesic circle.
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…
AceIRL learns expert reward from active exploration.
problem Learning reward function from expert demonstrations in unknown environments.
method Active exploration to infer reward function and identify good policy.
result First approach to active IRL with sample-complexity bounds that doesn't require a generative model.
SINGD improves KFAC for memory-efficiency and stability in low-precision training.
problem Memory inefficiency and numerical instability of KFAC in low-precision training.
method Formulated inverse-free KFAC update and imposed structures in Kronecker factors.
result SINGD is memory-efficient and numerically robust, often outperforming AdamW in half precision.
The paper proves new inequalities for convex hypersurfaces in hyperbolic and spherical spaces.
problem Proving new inequalities for convex hypersurfaces in hyperbolic and spherical spaces.
method Locally constrained inverse curvature flows in hyperbolic and spherical spaces.
result Established new Alexandrov-Fenchel and Minkowski inequalities involving general convex weight functions.