Paper proposes a neural network for generating better questions from text.
problem Automatic generation of relevant questions from sentences and paragraphs.
method Adaptive copying recurrent neural network model with a copying mechanism added to a bidirectional LSTM architecture.
result The model outperforms state-of-the-art methods in question generation metrics.
Dynamic question ordering improves survey completion and imputation quality.
problem Engage respondents and collect complete information for accurate imputations.
method Personalized question order based on earlier responses to maximize survey completion and imputation quality.
result Personalized question order increases survey completion and imputation quality.
The paper tackles adaptive questioning to classify candidate ability.
problem Designing an optimal sequence of adaptive questions to classify candidate ability.
method Develops lower bounds and geometrical insights for sequential questioning strategies, and arrives at algorithms that match these bounds.
result Asymptotically, any candidate needs to be asked questions at most at two levels, facilitating endogenous exploration.
We propose a new probabilistic graphical model that jointly models the difficulties of questions, the abilities of participants and the correct answers to questions in aptitude testing and crowdsourcing settings. We devise an active learning/adaptive testing scheme based on a greedy minimization of expected model entro…
Deep RL agent predicts malaria likelihood from household surveys.
problem Predicting malaria likelihood from household surveys.
method Deep Reinforcement Learning (DQN) agent learns to ask adaptive questions.
result 80% accuracy with 2.5 questions, vs. 6 questions for supervised learning.
Optimizes clustering from noisy binary feedback in crowdsourcing.
problem Clustering items from binary user feedback with noisy answers.
method Develops algorithms for clustering items using adaptive selection of questions and items.
result Adaptive algorithm achieves performance close to information-theoretical limits.
This study examines how reward scaling impacts non-saturating ReLU networks in reinforcement learning.
problem The impact of reward scaling on non-saturating ReLU networks in reinforcement learning.
method Proposes an Adaptive Network Scaling framework to find a suitable reward scale during learning.
result Empirical studies justify the effectiveness of the Adaptive Network Scaling framework.
EduQG generates better educational questions by pre-training on scientific text.
problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.
Paper introduces NumLLM for better financial text understanding with numeric variables.
problem Poor performance of existing financial large language models in numeric financial text.
method Constructed financial corpus, fine-tuned with LoRA modules, merged into foundation model.
result NumLLM achieves best performance on financial question-answering benchmark, especially with numeric questions.
This review categorizes domain adaptation methods without target labels.
problem How to train a classifier from a source domain to generalize to a target domain.
method Sample-based, feature-based, and inference-based methods.
result Recurring ideas and conditions for cross-domain generalization error.
Empirical study shows consistent meta-RL algorithms adapt to OOD tasks.
problem Theoretical consistency of meta-RL algorithms and its practical implications.
method Empirical investigation of representative meta-RL algorithms, focusing on consistency and adaptation to out-of-distribution tasks.
result Theoretical consistent algorithms can adapt to OOD tasks, while inconsistent ones cannot, but can still fail for poor exploration.
Paper explores BERT's efficiency on SQuAD2.0, freezing layers and using adapters.
problem Improving BERT's efficiency for SQuAD2.0 while maintaining performance.
method Freezing transformer layers, using adapters, and context-aware convolutional filters.
result Context-aware convolutional filters do not improve practical efficiency.
Optimal ability estimation in adaptive testing with binary responses.
problem Estimating a continuous ability parameter from sequential binary responses.
method Adaptive selection of questions to maximize Fisher information, updating estimate using method-of-moments, and deciding accuracy with a test statistic.
result Fisher-tracking strategy achieves optimal performance in fixed-confidence and fixed-budget regimes.
A version of smooth K-theory is constructed, which is adapted to the total Chern class instead of the Chern character (contrarily to previous theories). Some total Chern class morphism from this K-theory to Cheeger-Simons differential characters is constructed. This answers a question raised by U. Bunke.
Decentralized search algorithm for unknown target using noisy observations.
problem Adaptive search for an unknown target in a time-varying network.
method Decentralized 20 questions approach with social learning, using martingale-based techniques and spectral graph theory.
result Convergence to correct consensus on target value with stability and consistency guarantees.
Paper optimizes experimental design for estimating treatment effect.
problem Estimating treatment effect with heterogeneous subjects and treatments.
method Adaptive experimental design incorporating bandit learning.
result Demonstrates optimality of proposed adaptive experiment framework.
Calibration in 16D disproves Federer's product question.
problem Proving Federer's product question in 16D.
method Adapted Cayley calibration in R^16, constructing a specific calibration Φ.
result Product of two orthogonally supported calibrations is not always a calibration.
Target Date Funds may not adapt well, leading to poor performance.
problem Target Date Funds may not adapt to investors' needs effectively.
method Modeling with historical returns and bootstrap resampling to compare performance.
result Adaptive investment strategies significantly outperform Target Date Funds.
Structured pruning reduces large language model size and latency.
problem Reducing the size and latency of large language models.
method Parameterizing weights with low-rank factorization and adaptively removing rank-1 components.
result Structured pruning outperforms other methods at various compression levels and speeds up training and inference.
Domain adaptation and transfer learning help machine learning models adapt to new data distributions.
problem Machine learning models struggle with data distribution changes between training and test phases.
method Expands on risk minimization, discusses three types of data set shift, and various approaches to domain adaptation.
result Transfer learning and domain adaptation are essential for improving model performance in changing data environments.
AdaS adapts SGD learning rate based on knowledge gain metrics.
problem Empirical step-size selection in SGD optimization lacks consistency and insight.
method Introduces AdaS algorithm that adapts SGD learning rate based on knowledge gain metrics.
result AdaS outperforms existing adaptive learning methods in convergence and generalization.
Robo-advisors estimate clients' risk aversion using interactive questionnaires.
problem Estimating risk aversion of non-expert clients using adaptive questionnaires.
method Model risk aversion with cost functions and spectral risk measures. Use inverse reinforcement learning to design questions maximizing distinguishing power.
result Designing questions by maximizing distinguishing power achieves satisfactory accuracy in learning risk aversion with fewer than 50 questions.
Affirms link homotopy invariant definition and adapts Schneiderman-Teichner's invariant.
problem Defining and adapting link homotopy invariants.
method Adapting Schneiderman-Teichner's invariant to link maps and affirming Li's invariant.
result Adapted invariant τ τ τ coincides with Li's invariant ω ω ω . New adaptive scheme improves crowdsourcing accuracy with fixed budget.
problem Maximizing accuracy with limited crowdsourced responses.
method Generalized probabilistic model for adaptive task assignment.
result Adaptive scheme matches fundamental accuracy-budget trade-off.
ELF improves FM forecasts by efficiently using online feedback.
problem Fixed FMs fail to adapt to current data characteristics.
method ELF-Forecaster learns current data distribution, ELF-Weighter combines forecasts.
result ELF improves FM forecasts across various datasets.
This paper explores coordinates adapted to vector fields on smooth manifolds.
problem Finding coordinates where vector fields are smoother.
method Quantitative techniques from ODEs and PDEs.
result Results on smoothness and regularity of coordinates.
New method trains deep networks robustly without adaptive methods.
problem Training deep networks with robustness and efficiency.
method Scale invariant architecture + SGD + weight decay + gradient clipping.
result SGD can achieve similar performance to adaptive methods like Adam.
New algorithms learn MNL weights efficiently for any slate size.
problem Efficiently learn weights for MNL models given query access.
method Two algorithms: adaptive and non-adaptive, with specific query complexities.
result Optimal query complexities for both adaptive and non-adaptive cases.
New rates and adaptive algorithm for nonparametric active learning under noise conditions.
problem Establishing new minimax-rates for active learning under noise conditions.
method Generic algorithmic strategy for adaptivity to unknown noise smoothness and margin.
result Achieves optimal rates in many general situations and avoids adaptive confidence sets.
New method learns to answer questions from correct demonstrations without assuming bounded complexity of the demonstrator.
problem Learning to generate answers from correct demonstrations with multiple correct answers.
method Formalizes imitation learning in contextual bandits, relying on reward model complexity, not policy complexity.
result Achieves nearly optimal performance with sample complexity logarithmic in reward class cardinality.
Predicts student performance in interactive online question pools using GNNs.
problem Predicting student performance in interactive online question pools with evolving knowledge.
method Proposes R^2GCN, a GNN model for heterogeneous networks to predict student performance.
result Achieves higher accuracy in student performance prediction than traditional methods.
A new method for analyzing adaptive experiments using kernel treatment effects.
problem Efficiently analyzing adaptive experiments that adjust treatment assignments based on outcomes.
method Kernel Treatment Effects (KTE) framework combining RKHS scores and witness functions.
result Effective for both mean shifts and higher-moment differences, outperforming adaptive baselines.
CLEAR dataset for acoustic reasoning tasks.
problem Acoustic reasoning and question answering.
method Data generation from elementary sounds, functional programs for question composition.
result Validation of current state-of-the-art visual Q&A models on AQA task.
DiffQue estimates relative difficulty of questions in CQA services.
problem Estimating relative difficulty of questions in community Q&A services.
method Network-aided edge directionality prediction.
result DiffQue outperforms state-of-the-art methods by significant margins.
New framework tackles multi-source domain adaptation with optimism and consistency.
problem Adjusting mixture distribution weights and ensuring low error on target domain.
method Mildly optimistic objective function and consistency regularization.
result Beats current state of the art in multi-source domain adaptation.
BED-LLM uses Bayesian experimental design to improve LLMs' information gathering.
problem Improving LLMs' ability to gather information adaptively.
method Iteratively choosing questions to maximize expected information gain using a probabilistic model.
result BED-LLM achieves substantial performance gains compared to other adaptive design strategies.
New study shows non-adaptive trials can be outperformed by adaptive designs in treatment selection.
problem Determining the best allocation of resources in clinical trials.
method Analysis of batched arm elimination designs and comparison with completely randomized trials.
result Simple adaptive designs universally and strictly dominate non-adaptive completely randomized trials for at least three treatment arms.
Efficient algorithms for adaptive signal denoising are developed.
problem Signal denoising for discrete-time signals.
method Adaptive convolution-type estimators using first-order proximal algorithms.
result Efficient implementation and computational complexity analysis of adaptive estimators.
Framework for adaptive online learning with various bounds.
problem Adaptive online learning with model selection and data-dependent bounds.
method General framework using sequential complexity measures and one-sided tail inequalities.
result Demonstrates achievability of adaptive rates through offset complexity measures.
INFUSER improves reasoning by co-evolving a generator and solver with adaptive curriculum.
problem Improving reasoning in language models with minimal external supervision.
method INFUSER uses a Generator and Solver to co-evolve iteratively, rewarding the Generator with an influence score and the Solver with correctness rewards.
result INFUSER outperforms self-evolution baselines by over 20% on Olympiad and SuperGPQA benchmarks.
New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.
problem Designing online prediction algorithms that adapt to varying levels of non-stationarity.
method Epoch-based scheduling and non-uniform partitioning of the prediction space.
result Achieves adaptive calibration guarantees under multiple measures with optimal rates.
Study evaluates how well question-answering models generalize to new data types.
problem Generalization of question-answering models to new data types.
method Constructed new test sets from different domains and evaluated models' performance.
result Models show significant performance drops when tested on new data types.
Diffusion models adapt to low-dimensional data regardless of coefficient choices.
problem Understanding how diffusion models adapt to low-dimensional data structures.
method Analysis of diffusion models with flexible coefficient choices.
result Proven that O ~ ( k / ε ) \widetilde{O}(k/\varepsilon) O ( k / ε ) iterations suffice for accurate sampling in total variation distance. AI-assisted interviews allow respondents to describe experiences naturally, but mapping those accounts into structured survey variables is fallible.
problem Mapping AI-assisted interview responses into structured survey variables is fallible.
method Adaptive Matrix Validation (AMV) is proposed, which involves mapping responses into tabular data and using a small set of structured questions for statistical adjustment.
result The estimator calibrates mapped values using validation answers from other respondents and corrects remaining error with validation answers observed for the target respondent.
Improves dialogue state tracking across multiple domains.
problem Incomplete domain ontology limits DST models' adaptability.
method Model DST as Q&A, using evolving knowledge graph.
result 5.80% and 12.21% relative improvement on datasets.
The paper examines Adaptive Lasso and Transfer Lasso, highlighting their differences and proposing a new method.
problem Comparing and contrasting Adaptive Lasso and Transfer Lasso.
method Theoretical analysis of asymptotic properties and introduction of a new method.
result The Transfer Lasso method reduces non-asymptotic estimation errors compared to Adaptive Lasso.
Domain Adaptation in 6G wireless networks: When is it green?
problem Energy consumption of Domain Adaptation (UDA) compared to single-task training in 6G wireless networks.
method Investigate energy consumption and propose a method to determine the minimum number of target domains for UDA to be more energy-efficient than retraining.
result Proposed a method to determine the minimum number of target domains for UDA to be more energy-efficient than retraining.
Study the tradeoffs of bandit feedback in multiclass classification.
problem The price of using bandit feedback in multiclass classification.
method Mistake bound model, analysis of variants, and comparison of learners and adversaries.
result The optimal mistake bound under bandit feedback is at most O ( k ) O(k) O ( k ) times higher than in full information, with a tight bound of O ( k ) O(k) O ( k ) .