Self-supervised method detects active speaker from visual cues.
problem Improving robustness of language acquisition systems in noisy conditions.
method Visual detection of active speaker using self-supervised learning.
result Good performance in speaker dependent settings, lower in speaker independent settings.
Benchmark tests spoken language models for infant language learning.
problem Understanding how infants learn language from speech.
method Developed a language-acquisition-friendly benchmark.
result Benchmarking shows models' strengths and weaknesses.
Active testing for large language models is made more efficient and accurate.
problem Efficient evaluation of large language models with limited labels.
method Cost-saving measures and in-context learning for constructing a surrogate model.
result Significantly more accurate evaluations of LLM performance compared to random data acquisition.
Bal-PM reduces preference labeling costs for LLMs.
problem Efficiently acquiring human feedback for preference modeling in large language models.
method Bayesian Active Learning with entropy maximization in feature space.
result Bal-PM reduces the number of required preference labels by 33% to 68%.
Bayesian active learning improves natural language processing models.
problem Lack of model comparison in AL for NLP tasks.
method Large-scale empirical study of Bayesian active learning with Dropout and Bayes-by-Backprop uncertainty estimates.
result Bayesian active learning by disagreement significantly improves NLP model performance.
Study investigates predictive coding models for phonemic learning.
problem Understanding how predictive coding models generalize to different languages and dataset sizes.
method Investigated Autoregressive Predictive Coding and Contrastive Predictive Coding models in phoneme discrimination tasks for two languages with varying dataset sizes.
result Contrastive Predictive Coding model converges rapidly and outperforms Autoregressive Predictive Coding on both languages.
This paper proposes a new method to connect language and physical actions in reinforcement learning.
problem Connecting linguistic representations to the physical world in embodied agents.
method Language-conditioned goal generators to decouple sensorimotor learning from language acquisition.
result Agents can demonstrate a diversity of behaviors for any given instruction.
FunBO uses LLMs to discover effective acquisition functions for Bayesian optimization.
problem Designing optimal acquisition functions for Bayesian optimization across diverse problems.
method FunBO leverages FunSearch, an LLM, to learn and evaluate new acquisition functions.
result FunBO discovers acquisition functions that generalize well and outperform existing methods.
Human infants can discover words directly from unsegmented speech signals without any explicitly labeled data. In this paper, we develop a novel machine learning method called nonparametric Bayesian double articulation analyzer (NPB-DAA) that can directly acquire language and acoustic models from observed continuous sp…
Synthetic continued pretraining enhances model performance with synthetic data.
problem Data inefficiency in pretrained models when adapting to domain-specific documents.
method Synthetic data augmentation using EntiGraph to create a large synthetic corpus.
result Language models can answer questions and follow instructions without access to domain-specific documents.
Robot learns word meanings from perception-action tasks.
problem Language acquisition for robots.
method Affordance network with temporal co-occurrence of speech and actions.
result Robot forms useful word-to-meaning associations.
ProBO optimizes complex systems with flexible probabilistic models.
problem Optimizing expensive functions with minimal queries.
method Uses any probabilistic programming language to define models and optimize them.
result Demonstrates efficient optimization of complex models in BO.
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
Predicts programming languages from Stack Overflow questions and snippets.
problem Incorrectly tagging programming languages in Stack Overflow questions.
method Combines NLP features from titles, bodies, and code snippets for prediction.
result Combined features classifier achieves 91.1% accuracy.
This work tackles uncertainty quantification in language models, proposing a principled approach.
problem Challenges in identifying task-specific uncertainties in large language models.
method Bayesian decision theory, focusing on a similarity measure between generated and hypothetical true responses.
result Derives a measure for epistemic uncertainty based on a missing data perspective.
This paper considers a statistical signal processing problem involving agent based models of financial markets which at a micro-level are driven by socially aware and risk- averse trading agents. These agents trade (buy or sell) stocks by exploiting information about the decisions of previous agents (social learning) v…
Deep factorization machines improved SLAM task performance.
problem Improving second language acquisition modeling.
method Used deep factorization machines to model pairwise relationships.
result Achieved AUC 0.815, beating logistic regression baseline.
Tensor logic aims to unify AI types with scalable and transparent features.
problem Lack of a unified AI programming language with scalability and transparency.
method Introduces tensor logic, a new AI language based on tensor equations.
result Tensor logic enables key AI forms like transformers, formal reasoning, and graphical models.
The reparameterization trick simplifies optimization of acquisition functions in parallel Bayesian optimization.
problem Optimizing acquisition functions for parallel Bayesian optimization is challenging due to non-convexity, high dimensionality, and intractability.
method Formulate popular acquisition functions as Gaussian integrals and apply the reparameterization trick for gradient-based optimization.
result An efficient Monte Carlo estimator for the upper confidence bound acquisition function is derived.
Bayesian optimization uses acquisition functions to find optimal solutions efficiently.
problem Maximizing acquisition functions is difficult due to their complexity and non-convexity.
method Developed gradient-based optimization for Monte Carlo integration of acquisition functions and identified families of acquisition functions that can be maximized using greedy approaches.
result Greedy approaches can be used to maximize acquisition functions, making Bayesian optimization more practical.
Sell-side analysts' reports explain 10% of stock returns, with income statement analyses most impactful.
problem The value of sell-side analysts' information in predicting stock returns.
method Analysis of large language model embeddings and Shapley value decomposition.
result Income statement analyses contribute most to explaining stock returns.
Evidence acquisition costs influence disclosure behavior and preference.
problem How evidence acquisition costs affect disclosure behavior and preference.
method Analyzes sender-receiver interactions with covert and overt evidence acquisition, varying certification costs.
result Equilibria converge to the Pareto-worst free-learning equilibrium as costs vanish, and receivers prefer covert to overt acquisition.
NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.
problem Challenging environments for testing RL algorithms.
method Procedurally generated, stochastic, rich, and complex NetHack environment.
result Demonstrates empirical success for early stages of NetHack using RL.
AFA evaluates AI feature acquisition strategies in domains with high costs.
problem Evaluate AI feature acquisition strategies in domains with high costs.
method Apply missing data methods and offline reinforcement learning under NDE and NUC assumptions.
result Propose a novel semi-offline reinforcement learning framework with three new estimators.
Inexact acquisition solutions in BO lead to sublinear cumulative regret.
problem Inexact maximization of acquisition functions in Bayesian optimization.
method Define inaccuracy measure, establish cumulative regret bounds for GP-UCB and GP-TS.
result Inexact BO algorithms can achieve sublinear cumulative regret under appropriate inaccuracy conditions.
A new method for learning to defer decisions with expert advice improves over standard methods.
problem Learning to defer decisions with expert advice in systems where expert information can be modified after selection.
method An augmented surrogate that operates on the composite expert-advice action space, providing consistency guarantees and excess-risk bounds.
result The method improves over standard Learning-to-Defer and adapts its advice acquisition behavior to the cost regime.
A2MT learns agents to select which modalities to acquire at test time.
problem Learning agents to select modalities for multimodal temporal data acquisition.
method Perceiver IO architecture for active acquisition of multimodal temporal data.
result Agents successfully learn cost-reactive acquisition behavior on real-world datasets.
A simple method improves batch active learning without high compute.
problem Efficient batch active learning in machine learning.
method Adapting standard single-point acquisition strategies to batch.
result Simple strategy performs as well as advanced batch methods.
This paper explores optimising acquisition functions in Bayesian optimisation.
problem Optimising acquisition functions in Bayesian optimisation is challenging due to their non-convex nature.
method The authors derive compositional forms for acquisition functions and use them to recast maximisation as a compositional optimisation problem.
result The compositional approach to maximising acquisition functions shows empirical advantages across various tasks.
A new method uses LLMs to improve Bayesian optimization without requiring prior knowledge.
problem Improving Bayesian optimization with richer domain priors.
method Introducing agentic Bayesian optimization with an LLM agent as the central decision maker.
result Sara outperforms standard BO and LLM-based baselines, improving optimization with natural-language priors.
This paper optimizes Bayesian acquisition functions in Gaussian Processes for better optimization.
problem Improving the efficiency of Bayesian optimization methods.
method Analysis of different acquisition functions and optimizers for optimizing Bayesian acquisition functions.
result Optimization of acquisition functions leads to faster and more accurate sampling points.
ATS improves batch Bayesian Optimization by sampling multiple acquisition functions.
problem Efficiently optimizing multiple hyperparameters in parallel.
method ATS: sampling multiple acquisition functions from a stochastic process.
result ATS outperforms classical parallel Thompson Sampling and other batch BO methods.
NIFTY dataset for financial forecasting models.
problem Improving financial market forecasting with LLMs.
method Two datasets for supervised and reinforcement learning.
result Demonstrates applications in stock price prediction.
FUSE improves verification quality without ground truth labels.
problem Verification of model outputs using imperfect judges and reward models.
method Ensembling verifiers without ground truth labels using spectral algorithms.
result FUSE matches or improves upon semi-supervised alternatives in test-time scaling experiments.
Memory-based adaptation speeds up neural network learning.
problem Slow adaptation of neural networks to changing data.
method Stores examples in memory and uses context-based lookup to modify weights.
result Higher learning rates lead to better performance on new data.
Optimizes information acquisition to reduce estimation risk and maximize utility.
problem Estimation risk in investor decision-making.
method Derives closed-form value functions using CARA and CRRA utility functions, employs variational methods to explore optimal acquisition.
result Acquiring information earlier is more valuable in reducing estimation risk and achieving higher utility.
Optimizes data acquisition in high-dimensional Bayesian optimization.
problem Suboptimal data acquisition in high-dimensional Bayesian optimization tasks.
method Utility-calibrated variational inference to align approximations with BO goals.
result Optimal data acquisition decisions under a limited computational budget.
Efficiently reduces computational burden of rollout acquisition functions in Bayesian optimization.
problem Expensive computation of rollout acquisition functions in Bayesian optimization.
method Combines quasi-Monte Carlo, common random numbers, and control variates to reduce computational burden. Formulates a policy-search approach to eliminate the need to optimize the rollout acquisition function.
result Significant reduction in computational burden of rollout acquisition functions.
NM-PPG optimizes adaptive feature acquisition in POMDPs for better predictions.
problem Optimizing adaptive feature acquisition in prediction problems with costly features.
method Non-myopic pathwise policy gradients (NM-PPG) with continuous relaxation and straight-through rollout.
result NM-PPG outperforms state-of-the-art AFA methods on synthetic and real-world datasets.
Boundary effects inflate variance in Gaussian processes, leading to acquisition bias.
problem Boundary-induced acquisition bias in Gaussian processes.
method Traced root cause to geometric mechanism of kernel truncation at domain boundaries.
result Boundary effects create distortion that worsens with dimensionality, affecting acquisition behavior.
A framework for cost-effective feature selection in classification.
problem Sequentially selecting features to maximize prediction performance at minimum cost.
method Formulated as a reinforcement learning problem, a joint learning framework for RL agent and classifier is introduced. Orderless LSTM-based set encoding is used for feature subsets.
result Outperforms all baselines in prediction performance and feature acquisition cost on synthetic and real datasets.
BatchBALD selects multiple informative points for deep Bayesian active learning, improving data efficiency.
problem Efficient and diverse selection of points for deep Bayesian active learning.
method Develops BatchBALD, a greedy linear-time approximation to mutual information, as an acquisition function.
result Achieves new state-of-the-art performance on benchmarks, improving data efficiency.
Unified framework connects EI and information-theoretic acquisition functions.
problem Distinguish between Expected Improvement and information-theoretic acquisition functions.
method Introduces Variational Entropy Search (VES) to unify EI and information-theoretic approaches.
result EI can be seen as a variational inference approximation of Max-value Entropy Search (MES).
Proposes a new acquisition function for batched Bayesian optimization.
problem Intractability of acquisition functions for batched Bayesian optimization.
method Statistical physics inspired acquisition function for Gaussian processes.
result Demonstrates competitive performance on various problems.
Dynamic acquisition of features improves predictions with limited data.
problem Limited or uncertain data requires additional relevant information for accurate assessments.
method Proposes models that dynamically acquire new features using conditional mutual information and arbitrary conditional flow.
result Demonstrates superior performance over baselines in multiple settings.
This paper optimizes sampling policies for Bayesian optimization to improve exploration and exploitation.
problem Improving the balance between exploration and exploitation in Bayesian optimization.
method Developed efficient methods to estimate and optimize non-myopic acquisition functions using rollout policies and stochastic gradient optimization.
result Efficient optimization of sampling policies leads to better performance in Bayesian optimization.
New acquisition function improves batch Bayesian active learning.
problem BatchBALD conflates epistemic and aleatoric uncertainty, leading to suboptimal performance.
method Focus on predictive probabilities to separate epistemic uncertainty, leading to better performance and faster evaluation.
result The new acquisition function performs better and allows for larger batches.
This paper analyzes local optimizers in Bayesian optimization for expensive functions.
problem Finding global optimizers in Bayesian optimization is challenging and time-consuming.
method The paper analyzes three acquisition functions (PI, EI, GP-UCB) and their local optimizers.
result Local optimizers can be used effectively in Bayesian optimization, reducing search time.