Efficiently selects top-m designs for various contexts using sequential sampling.
problem Optimizing selection of top-m designs across different contexts.
method Formulated as a stochastic dynamic programming problem, developed sequential sampling policy.
result Asymptotically optimal sampling ratios for efficient selection.
NOTMAD estimates context-specific Bayesian networks without breaking datasets.
problem Non-convexity of acyclic graphs limits sharing information between context-specific estimators.
method NOTMAD models context-specific Bayesian networks as mixtures of archetypal DAGs, estimating structures and parameters jointly.
result NOTMAD shares information between context-specific acyclic graphs, enabling single-sample resolution.
Thompson Sampling tackles noisy context in stochastic bandits.
problem Designing an action policy for noisy, corrupted contexts in stochastic bandits.
method Introducing a Thompson Sampling algorithm for Gaussian bandits with Gaussian context noise, adopting an information-theoretic analysis.
result Demonstrates the Bayesian regret of the proposed algorithm concerning the oracle's action policy.
We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommende…
The paper tackles long-context linear system identification with improved sample complexity bounds.
problem Identifying dynamical systems with long dependencies over fixed context windows.
method Established sample complexity bounds for systems with linear dependencies over a context window of length p.
result The learning process is not hindered by slow mixing properties in extended context windows.
NERS improves RL by sampling diverse transitions considering local and global contexts.
problem Sampling biases in experience replay lead to redundant transitions.
method Neural Experience Replay Sampler (NERS) that considers both local and global contexts.
result NERS significantly improves RL performance by sampling diverse and meaningful transitions.
LLMs generate answers under incomplete context, and their uncertainty should scale with missing information.
problem Evaluating the quality of LLM answers under incomplete context.
method A controlled framework with varying context availability, and two uncertainty measures (sampling-based confidence and response entropy) evaluated on SQuAD.
result Response entropy increases with context removal and explains more variance in accuracy than confidence, suggesting it is a more responsive uncertainty measure.
Paper studies linear CMDPs, improving sample complexity for both models.
problem Improving sample complexity for linear CMDPs.
method Proposes novel model-based algorithms for two linear function approximation models.
result Guaranteed ε-suboptimality gap with desired polynomial sample complexity.
Contextualized ML learns context-dependent effects using deep learning.
problem Learning heterogeneous and context-dependent effects in data.
method Applying deep learning to the meta-relationship between contextual information and context-specific parametric models.
result Unified framework for cluster analysis and cohort modeling.
Improves NMT by sampling context from predicted sequence during training.
problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.
Algorithm identifies best arm in piecewise stationary linear bandits with minimal samples.
problem Identifying the best arm in a piecewise stationary linear bandit model with unknown contexts and changepoints.
method Design of PS ε \varepsilon ε BAI + ^+ + algorithm, consisting of PS ε \varepsilon ε BAI and N ε \varepsilon ε BAI subroutines. result PS ε \varepsilon ε BAI + ^+ + achieves optimal sample complexity up to a logarithmic factor. New Thompson Sampling for partially observed context bandits reduces regret logarithmically with time.
problem Improving Thompson Sampling for partially observed context bandits.
method Proposed a Thompson Sampling algorithm for partially observable contextual multi-armed bandits with theoretical performance guarantees.
result Regret scales logarithmically with time and the number of arms, and linearly with the dimension.
Minimax PAC bounds for learning in exogenous contextual MDPs
problem PAC learning in tabular discounted Markov decision processes with exogenous i.i.d. contexts
method Variance-reduced algorithm for policy evaluation, best-value estimation, and best-policy extraction
result Minimax optimal sample complexity
Bayesian Attention Networks compress data by focusing on key training samples.
problem Lossless data compression for efficiency.
method Bayesian Attention Networks with attention factors and latent space.
result Efficient prediction using a few correlated training samples.
TTT improves transformer models for in-context learning.
problem Improving transformer models for efficient in-context learning.
method Gradient-based TTT method for linear transformers, with theoretical and empirical analysis.
result TTT significantly reduces the sample size required for in-context learning.
Improves sample efficiency in reinforcement learning by controlling task distribution.
problem Learning and generalization of behaviors across related tasks in intelligent robots.
method Introduces a novel relative entropy reinforcement learning algorithm that allows the agent to control the intermediate task distribution.
result The proposed curriculum learning scheme drastically improves sample efficiency and enables learning in challenging scenarios.
Diffusion models learn hierarchical composition rules from data.
problem How many samples do generative models need to learn hierarchical composition rules?
method Theoretical and empirical investigation of diffusion models on probabilistic context-free grammars.
result Diffusion models learn hierarchical composition rules with sample complexity scaling polynomially with context size.
Paper tackles binary feedbacks in contextual search learning.
problem Learning underlying mean value function in context with binary feedbacks.
method Tri-section search combined with margin-based active learning.
result Algorithm achieves O ( 1 / ε 2 ) O(1/\varepsilon^2) O ( 1/ ε 2 ) queries for ε ε ε -estimation accuracy. A new approach learns to represent context for nonstationary bandits.
problem Nonstationary contextual bandits where patterns change over time.
method Combines recurrent neural networks with contextual linear bandit algorithm.
result Consistently outperforms handcrafted historical contexts and other methods.
Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.
problem Efficiently adapt and explore in-context without gradient-based updates.
method Uses a transformer to learn inference from training tasks, considering hypothesis space of partial models.
result Adaptation speed and exploration-exploitation balance approach those of an exact posterior sampling oracle.
Algorithm identifies Pareto front using multiple context directions and reuses exploration samples.
problem Identifying a set of arms with undominated mean reward vectors in linear bandits.
method Proposes a new estimator that updates estimates along multiple context directions and reuses exploration samples.
result Optimal sample complexity and logarithmic regret compared to optimal algorithms.
New algorithm learns optimal decisions from imperfectly observed contexts.
problem Learning optimal decisions in bandits with unobserved contexts.
method Posterior sampling algorithm for imperfectly observed contexts.
result Efficient learning from noisy imperfect observations.
The paper develops a new framework for detecting distributional drifts conditioned on context.
problem Detecting distributional drifts in machine learning systems when context changes.
method Develops a framework using two-sample tests for conditional distributional treatment effects.
result Demonstrates effectiveness for detecting drift in subpopulations of data.
INFERS PDEs from data samples using learned context.
problem Inferring explicit PDEs from unseen dynamics.
method Contextual Finite Differences (CFD) method integrating PDE form and differential scheme.
result Yields a PDE fitting the data sample for signal prediction and explanation.
This work improves local differential privacy by considering context to make it more effective.
problem Local differential privacy often sacrifices utility, especially for sensitive data.
method Introduces context-aware local differential privacy, optimizing privacy and utility.
result Contextual information can reduce the number of samples needed for privacy compared to classical LDP.
A new algorithm improves regret bounds for contextual bandits.
problem Complexity of missing data in multi-armed bandits.
method Doubly Robust (DR) Thompson Sampling with contexts.
result Improved regret bound with i l d e O ( d T ) ilde{O}(d\sqrt{T}) i l d e O ( d T ) . DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.
problem Pathologies in standard policy gradients, leading to poor updates and over-allocation of gradient budget.
method Introduces Delightful Policy Gradient (DG) that gates each term with a sigmoid of advantage and surprisal.
result DG provably improves directional accuracy in a single context and shifts the expected gradient closer to the oracle across multiple contexts.
A new bandit model with stochastic context distributions and UCB algorithm.
problem Learning optimal actions in a stochastic environment with hidden contexts.
method Stochastic contextual bandit model and UCB algorithm.
result Order-optimal high-probability bound on cumulative regret for linear and kernelized reward functions.
New language model shows context length impacts generation quality and reasoning ability.
problem Analyzing the impact of context length and reasoning on autoregressive generation.
method Introduced synthetic hierarchical languages, used an exact k-gram ansatz, derived asymptotic predictions, and validated empirically.
result Reasoning models with limited context can generate sequences from the true language, improving exponentially over standard models.
DDPMs can reproduce medical image context, showing interpolation between samples.
problem Understanding DDPMs' ability to learn spatial context in medical imaging.
method Used stochastic context models (SCMs) to produce training data and assess DDPMs' performance.
result DDPMs can generate contextually correct images, interpolating between samples.
WildWood improves Random Forest predictions using bootstrap out-of-bag samples.
problem Improving Random Forest predictions for supervised learning.
method Uses bootstrap out-of-bag samples to compute improved predictions by aggregating all possible subtrees with exponential weights.
result WildWood produces faster and more competitive predictions compared to other ensemble methods.
TL-ANDI distills context from source data to improve transfer learning for TFMs.
problem Limited transfer learning due to context-size constraints and distribution shifts.
method TL-ANDI uses posterior-aware distillation to construct a compact source context and locally distills labels.
result Improves transfer performance by addressing context-size and distribution shifts.
Generative AI can solve in-context learning problems using a martingale perspective.
problem Estimating when a conditional generative model can solve an in-context learning problem.
method Bayesian interpretation, ancestral sampling, generative predictive p-value.
result Developed a method to assess the suitability of CGMs for ICL problems using generative predictive p-values.
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art anomaly scores are still based on the reconstruction error, which lacks in two e…
Thompson Sampling improves decision-making in partially observed contexts.
problem Balancing exploration and exploitation in partially observed contextual bandits.
method Thompson Sampling policy for learning optimal arms from noisy linear functions of unobserved context vectors.
result Thompson Sampling achieves poly-logarithmic regret and square-root consistency of parameter estimation.
Simplifies BO by directly sampling from posterior, achieving 35x efficiency.
problem Optimizing expensive functions with Bayesian Optimization.
method Direct sampling from posterior using a pre-trained generative model.
result Achieves 35x efficiency gain over Gaussian process-based BO.
This study examines how sequential correlations affect in-context learning in sequence models.
problem Understanding how in-context learning works with sequentially correlated data.
method Extended linear regression model to sequentially correlated data, tested on transformer architectures.
result Sequential correlations alter the effective context length and attention architecture effectiveness.
Transformers learn low-dimensional target functions efficiently in-context.
problem Efficiently learning nonlinear target functions in-context using transformers.
method Nonlinear MLP layer in transformers optimized by gradient descent, focusing on single-index target functions.
result Transformers can learn target functions with low-dimensional structures efficiently in-context.
Paper proposes linear transformers for efficient in-context learning without context length limitations.
problem Quadratic complexity of softmax transformers limits data processing speed.
method Investigates linear transformers under domain generalization, showing they learn mappings from context distributions to response functions.
result Linear transformers achieve in-context learning with a linear complexity in context length, offering a dimension-independent convergence rate.
We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared with grid sampling and uniform sampling techniques, it achieves higher generalization performance. We validate the strategy on two artificial…
Bayesian Context Trees improve change-point detection in discrete data.
problem Detecting and segmenting change-points in discrete time series data.
method Bayesian Context Trees framework, Markov chain Monte Carlo sampling.
result Effective sampling from posterior distribution of change-points.
This research improves graph embeddings by optimizing node sampling with centrality weights.
problem Improving the accuracy and efficiency of graph embeddings using Skip-Gram methods.
method Implemented and analyzed four graph embedding techniques with different centrality-weighted sampling distributions.
result Centrality-weighted sampling leads to improved accuracy and faster learning times.
This work introduces a method to decompose uncertainty in in-context learning for large language models.
problem Understanding the sources of uncertainty in in-context learning for large language models.
method Variational uncertainty decomposition framework without sampling from latent parameter posterior.
result Quantitative and qualitative validation of decomposed epistemic and aleatoric uncertainties.
In-context learning solves PU classification without iterative optimization.
problem Binary classification with only labeled positives and unlabeled samples.
method Pretrained transformer (PUICL) that learns from synthetic PU datasets.
result Outperforms four standard PU learning baselines on 20 benchmarks.
ContextFlow++ improves generative models by conditioning on mixed-variable contexts.
problem Lack of effective methods for context conditioning in flow-based generative models.
method Proposes ContextFlow++ with additive conditioning and mixed-variable architecture.
result ContextFlow++ achieves higher performance metrics and faster training.
Bayesian optimization for contextual policy search improves robot learning.
problem Scalable robot learning with limited data.
method Factored contextual representation using target and environment contexts.
result Experience can be generalized over target contexts, leading to faster learning and better generalization.
Enhances neural processes to learn from multiple related datasets.
problem Improving predictions from datasets with shared similarities.
method Developed the in-context in-context learning pseudo-token TNP (ICICL-TNP) to condition on both sets of datapoints and sets of datasets.
result Demonstrated the importance and effectiveness of in-context in-context learning.
Unified framework for ICL in causal and masked models.
problem Understanding ICL in masked language models and comparing it to causal models.
method Developed a statistical learning framework representing context by empirical measure and predicting using context and query.
result Upper bounds for masked and autoregressive objectives under Wasserstein-type regularity conditions.