Efficient algorithms for contextual slate bandits with limited adaptivity.
problem Contextual slate bandit problem with limited adaptivity.
method Proposed B-SlateGLinCB and RS-SlateGLinCB algorithms for batched and rarely-switching settings.
result Achieved regret bounds of O(Nd^(3/2)√T) and O(Nd√T) under diversity assumption.
Study exact community recovery in noisy SBM with limited queries.
problem Community recovery in noisy stochastic block models with limited queries.
method Balanced uniform querying, two-stage adaptive strategy, sublinear queries, subsampled graph.
result Adaptive querying can improve exact recovery limits in noisy SBM.
Bayesian approach improves speech recognition with limited speaker data.
problem Reduces mismatch between training and evaluation data due to speaker differences.
method Bayesian learning for DNN adaptation models with limited speaker data.
result Bayesian adaptation consistently outperforms deterministic methods, reducing word error rates up to 1.4%.
Adaptive sampling detects local concept drift with limited labels.
problem Detecting local concept drift in dynamic environments with scarce labels.
method Combines residual-based exploration and exploitation with EWMA monitoring.
result Superior performance in label efficiency and drift detection accuracy.
Study shows algorithms benefit from limited target data with many source domains.
problem Adapting to new domains with scarce labeled target data.
method New family of model selection algorithms.
result Beneficial guarantees in scenarios with limited target data.
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
Two algorithms address limited adaptivity in generalized linear contextual bandits.
problem Limited adaptivity in generalized linear contextual bandits.
method Two algorithms, B-GLinCB and RS-GLinCB, designed for two settings of limited adaptivity.
result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret in both settings. Adaptive kernels from neural networks improve model performance.
problem Improving neural network performance through adaptive kernels.
method Deriving adaptive kernels from infinite-width neural networks using feature learning and gradient flow training.
result Adaptive kernels achieve lower test loss compared to traditional kernels.
New method uses limited labeled data and multiple starts to adapt models across domains.
problem Accurate predictions in target domain with few labeled data.
method Fine-tuning from multiple adaptive starts, extending UDA methods.
result Minimax-optimal target performance with limited labeled target data.
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.
Derives effective continuous dynamics for adaptive SGD methods.
problem Analyzing noise in adaptive SGD methods.
method Stochastic modified equations framework and Malladi's scaling rules.
result Sampling-induced noise in SGD limits to independent Brownian motions.
A new algorithm reduces inference error in adaptive contextual bandits.
problem Challenges in statistical inference for adaptive contextual bandits.
method Proposes a regularized EXP4 algorithm that satisfies the Lai-Wei stability condition.
result Valid Wald-type confidence intervals for linear functionals can be achieved without the price of adaptivity.
Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method -- W \mathbf{W} W -decorrelation -- for transformi…
LinUCB algorithm handles adaptive sampling biases for linear bandits.
problem Adaptive sampling introduces biases in statistical inference.
method LinUCB algorithm with stability property for linear bandits.
result LinUCB achieves asymptotic normality with Wald-type confidence sets.
Adaptive optimal transport priors improve few-shot learning robustness.
problem Limited supervision and distribution shifts in few-shot learning.
method Prototype-Guided Distributionally Robust Optimization (PG-DRO) framework.
result PG-DRO achieves stronger robust generalization in few-shot scenarios.
Paper tackles offline RL with limited target samples using domain adaptation.
problem Limited samples in target dataset degrade offline RL performance.
method Proposes a framework to balance target and source datasets with theoretical guarantees.
result Establishes performance bounds and optimal weight for offline RL.
Adaptive market-making strategy improves profit by adjusting to order flow.
problem Optimizing market-making profits in a dynamic market environment.
method Closed-form solutions for optimal bid-ask spreads, modeling demand randomness, and adapting to market order behavior.
result Adaptive strategies outperform fixed and non-adaptive strategies.
Given a small corpus D T \mathcal D_T D T pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of D T \mathcal D_T D T . These embeddings may be used in various tasks involving D T \mathcal D_T D T . A popular strategy in limited…
Efficient inference method for adaptive experiments with tighter confidence sequences.
problem Efficient inference of Average Treatment Effect in a changing policy sequential experiment.
method Semiparametric efficient inference using Adaptive Augmented Inverse-Probability Weighted estimator and asymptotic confidence sequences.
result Derives tighter confidence sequences for adaptive experiments under data-dependent stopping times.
IntelligentPooling learns personalized mHealth policies from limited data.
problem Challenges in personalizing mHealth policies with limited user data and noise.
method Adaptive use of other users' data to learn personalized policies.
result Achieves 26% lower regret compared to state-of-the-art approaches.
We analyze the computational limits of LoRA for transformer models using fine-grained complexity theory.
problem Computational efficiency of LoRA fine-tuning for transformer models.
method Fine-grained complexity theory, identifying phase transitions, almost linear algorithms.
result Existence of almost linear algorithms for LoRA adaptation based on specific norms.
New insights into SGD and SGD-M in high dimensions.
problem Understanding and comparing SGD and SGD-M in high-dimensional settings.
method Developed high-dimensional scaling limits for SGD-M and online SGD, examining their dynamics and performance.
result SGD-M amplifies high-dimensional effects, potentially degrading performance compared to online SGD.
Extends Penrose limit to Finsler spacetimes.
problem Extending Penrose limit to Finsler spacetimes.
method Introducing lightlike coordinates and adapting Lorentzian pp-wave definition.
result New examples of Finsler pp-waves presented.
Study finds exact limits for sparse regression with fewer observations than usual.
problem Understanding sparse linear regression with sublinear sparsity.
method Adaptive interpolation method and modified AMP algorithm.
result Exact asymptotic expressions for mutual information and MMSE in sublinear sparsity.
New theory for clustering in geometric and adaptive settings.
problem Clustering in non-Euclidean spaces and adaptive parameters.
method Asymptotic theory for k k k -means and related methods. result Strong consistency and asymptotic limit theorems for various clustering procedures.
Graph-based weather prediction adapted for local models.
problem Applying neural weather prediction to limited area modeling.
method Adapting graph-based Neural Weather Prediction approach to local models.
result Validation of multi-scale hierarchical model extension for Nordic region.
The paper calculates curvature limits and Gauss-Bonnet theorems in the Heisenberg group.
problem Computing curvature limits and Gauss-Bonnet theorems in the Heisenberg group.
method Sub-Riemannian limits of Gaussian curvature, Schouten-Van Kampen affine connections, and adapted connections.
result Gauss-Bonnet theorems associated with Schouten-Van Kampen affine connections in the Heisenberg group.
Two algorithms achieve optimal regret with limited adaptivity in multinomial logistic bandits.
problem Achieving optimal regret with limited adaptivity in multinomial logistic bandits.
method Presented two algorithms, B-MNL-CB and RS-MNL, for batched and rarely-switching paradigms.
result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret with limited adaptivity. We endow projective (resp. direct) limits of Banach tensor structures with Fréchet (resp. convenient) structures and study adapted connections to G G G -structures in both frameworks. This situation is illustrated by a lot of examples.
RAID algorithm detects anomalies in real-time IoT systems.
problem Anomaly detection limitations in multivariate dynamic processes.
method Adapts to non-stationary effects and handles data drift.
result Improved detection accuracy and root cause isolation.
Study adaptive clinical trial methods for identifying patient subpopulations with treatment benefit.
problem Adaptive identification of patient subpopulations with treatment benefit in clinical trials.
method Proposes AdaGGI and AdaGCPI meta-algorithms for subpopulation construction.
result Empirical investigation of AdaGGI and AdaGCPI performance across various simulation scenarios.
We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making. While the greedy policy is known to perform well for a wide variety of adaptive stochastic optimization problems in practice, its theoretical properties have been analyzed only for a limited class of p…
Adaptive Monte Carlo schemes developed over the last years usually seek to ensure ergodicity of the sampling process in line with MCMC tradition. This poses constraints on what is possible in terms of adaptation. In the general case ergodicity can only be guaranteed if adaptation is diminished at a certain rate. Import…
Study on adaptivity constraints in linear contextual bandits with optimal design.
problem Impact of adaptivity constraints on linear contextual bandits.
method Two models of limited adaptivity: batch learning and rare policy switches. Proposed distributional optimal design.
result Achieves minimax-optimal regret with optimal number of policy switches and batches.
Develops a flexible batched experimentation framework for limited adaptivity.
problem Challenges of continual reallocation in bandit algorithms with delayed feedback.
method Computational framework leveraging Gaussian sequential experiment and dynamic programming.
result Improves statistical power over standard methods, even compared to Bayesian bandit algorithms.
Recent breakthrough results in compressive sensing (CS) have established that many high dimensional signals can be accurately recovered from a relatively small number of non-adaptive linear observations, provided that the signals possess a sparse representation in some basis. Subsequent efforts have shown that the perf…
LoRA fine-tuning on CPUs without GPUs achieves comparable performance to GPU-based methods.
problem Limited computational resources for fine-tuning LLMs.
method Developed a CPU-efficient method to learn meta-operators for LoRA weights.
result LoRA adapters trained on CPUs outperform base models on downstream tasks.
New method improves domain adaptation by aligning sub-domains.
problem Real-world domain adaptation with shifted class distributions.
method Rebalanced sub-domain alignment and novel generalization bound.
result Improves performance in shifted class distribution scenarios.
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.
The recent trend for acquiring big data assumes that possessing quantitatively more and qualitatively finer data necessarily provides an advantage that may be critical in competitive situations. Using a model complex adaptive system where agents compete for a limited resource using information coarse-grained to differe…
Finite-precision learning of a n h anh anh networks is limited by the Monte Carlo rate.
problem Learning a n h anh anh neural networks under finite precision method Using iterated a n h anh anh activations to construct localized bump functions result No adaptive randomized algorithm can achieve higher convergence rate than Monte Carlo rate in finite precision
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
Research shows minimal communication limits adaptive function estimation rates.
problem Adaptive estimation of a smooth function under minimal communication constraints.
method Investigates the L ∞ L_\infty L ∞ -risk and L 2 L_2 L 2 -risk under different numbers of servers. result For L ∞ L_\infty L ∞ -risk, optimal rates cannot be achieved under minimal communication. For L 2 L_2 L 2 -risk, adaptivity is possible but depends on server number and sample size. Study designs for estimating treatment effects in adaptive experiments.
problem Estimating treatment effects under adaptive treatment assignment.
method Propose and analyze IPW and AIPW estimators, establish CLTs under design stability.
result Central limit theorems for IPW and AIPW estimators under design stability.
A new data-adaptive prior stabilizes kernel learning in operators.
problem Learning kernels in operators from data is ill-posed due to nonlocal dependence.
method Introduces a data-adaptive prior to stabilize the Bayesian posterior mean.
result The data-adaptive prior achieves a stable posterior with small noise limits.
Method evaluates classification uncertainty with adaptively chosen features.
problem Finding a balance between model efficiency and fairness.
method Adaptively selects features for equalized coverage in classification.
result Valid and effective method demonstrated on simulated and real data.
Polyak-Ruppert CLT for SA-Adam with momentum and non-convergent adaptive preconditioning
problem Adaptive optimizers combining momentum and non-convergent preconditioning
method Proving positive drift stability and a non-autonomous Polyak-Ruppert CLT for SA-Adam
result The iterate-marginal covariance is exactly the plain stochastic gradient descent (SGD) sandwich
Best-of- ∞ \infty ∞ improves LLM performance by efficiently allocating inference-time computation.
problem Achieving optimal performance in test-time LLM ensembling with infinite budget.
method Adaptive generation scheme and weighted ensembles of LLMs, formulated as mixed-integer linear program.
result Optimal ensemble weighting improves performance over individual models.