Transformers can implement reinforcement learning algorithms from data without updates.
problem Training reinforcement learning algorithms from data without parameter updates.
method Design a teacher-mimicking training procedure for transformers to implement policy-improvement methods.
result Gradient flow converges to an optimal parameter manifold corresponding to the desired RL update.
ICEE learns new RL tasks in less time with a Transformer model.
problem Efficient in-context policy learning for reinforcement learning.
method In-context Exploration-Exploitation (ICEE) algorithm that optimizes efficiency without explicit Bayesian inference.
result ICEE solves Bayesian optimization problems as efficiently as Gaussian process biased methods but in significantly less time.
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
Transformers learn to play games in-context, proving Nash equilibrium.
problem Understanding in-context game-playing capabilities of pre-trained transformers.
method Theoretical guarantees and constructional results for transformer architecture in multi-agent games.
result Pre-trained transformers can learn Nash equilibrium in-context for two-player zero-sum games.
Paper explores using LLMs for zero-shot reinforcement learning in continuous spaces.
problem Leveraging LLMs for continuous state spaces in reinforcement learning.
method Disentangled In-Context Learning (DICL) to handle multivariate data and control signal.
result DICL produces well-calibrated uncertainty estimates in reinforcement learning settings.
Free Random Projection enhances reinforcement learning by naturally incorporating hierarchical structure.
problem Improving reinforcement learning algorithms for better generalization and adaptability.
method Introduces Free Random Projection, a method that uses free probability theory to create random orthogonal matrices encoding hierarchical structure.
result Empirically shows consistent improvement in generalization over standard methods on multi-environment benchmarks.
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.
TAMO optimizes multiple objectives in-context using transformers.
problem Balancing competing objectives in expensive, black-box problems.
method Fully amortized, transformer-based policy for multi-objective optimization.
result Significant speedup in proposal time with improved Pareto quality.
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.
MLPs can approximate any function in context, challenging the importance of in-context universality.
problem Understanding why transformers are more effective than classical models.
method Proved MLPs with trainable activation functions are universal in context.
result Transformer success is likely due to factors other than in-context universality.
Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.
problem Fine-tuning harms in-context learning, reducing zero-shot performance on unseen tasks.
method Theoretical analysis of linear attention models, identifying conditions for degraded few-shot performance.
result Restricting updates to the value matrix improves zero-shot performance while preserving in-context learning.
Transformers show better in-context learning resilience under distribution shifts than simple MLPs.
problem Understanding in-context learning under varying distribution shifts.
method Comparing transformers and set-based MLPs on linear regression tasks.
result Transformers better emulate OLS performance and exhibit better resilience to mild distribution shifts.
LLMs learn probability density functions in-context, showing distinct learning trajectories.
problem Density estimation of time series data in LLMs.
method Intensive Principal Component Analysis (InPCA) to visualize and analyze LLMs' learning dynamics.
result LLMs follow similar learning trajectories in a low-dimensional InPCA space, distinct from traditional methods.
Transformers learn to perform logistic regression in-context.
problem Understanding how transformers learn to perform specific tasks in-context.
method Constructed multi-layer transformers that perform in-context logistic regression through normalized gradient descent.
result Transformers can be trained to perform in-context logistic regression effectively.
Continuum transformers learn operators in context via gradient descent.
problem Generalizing transformers to handle infinite-dimensional inputs for in-context learning.
method Gradient descent in an operator RKHS, leveraging generalized representer theorems and gradient flows.
result Operator learned in context is Bayes Optimal Predictor in infinite depth limit.
Transformers forecast time series in-context, improving efficiency and performance.
problem Overfitting and limited performance in time series forecasting.
method Reformulate time series forecasting as input tokens, aligning with in-context learning mechanisms.
result Consistently better performance across various settings (full-data, few-shot, zero-shot).
Transformers can adaptively select and perform various machine learning tasks in context.
problem Transformers' ability to perform multiple machine learning tasks without explicit prompting.
method Statistical theory and efficient implementation of in-context gradient descent, enabling transformers to implement various algorithms and tasks.
result Transformers can implement a broad class of standard machine learning algorithms in context, including algorithm selection.
New framework shows cross-attention improves multi-modal in-context learning.
problem Understanding multi-modal in-context learning in neural networks.
method Mathematical framework and linearized cross-attention mechanism.
result Cross-attention mechanism is provably optimal for multi-modal in-context learning.
New analysis shows transformer models can't learn effectively.
problem Transformer models learning in context can't achieve general predictive accuracy.
method Empirical evidence and mathematical analysis of transformer architecture limitations.
result Transformers cannot achieve general predictive accuracy due to architectural limitations.
New model uses attention for in-context learning of categorical data.
problem Learning from categorical data in context.
method Attention-based network with self-attention and cross-attention layers, using functional gradient descent.
result Model can perform multi-step inference for categorical observations.
Transformers learn new tasks from few examples via optimal approximation.
problem Learning new tasks from limited examples using large language models.
method Developed approximation and generalization error bounds for transformers trained on nonparametric regression tasks.
result Transformers achieve minimax optimal estimation risk in context.
LLMs perform well in financial sentiment analysis without fine-tuning.
problem Challenges in financial terminology, emotions, and ambiguous expressions.
method In-context learning methods for financial document-sentiment pairs.
result LLMs can generalize in-context demonstrations to new financial documents.
Paper presents a Transformer model for automatic domain adaptation.
problem Challenges in selecting or designing domain adaptation algorithms.
method Transformer model approximates and selects domain adaptation algorithms.
result Transformers can approximate and automatically select domain adaptation algorithms.
Study on neural scaling laws for solving linear systems in-context.
problem Theoretical guarantees for solving linear systems using a linear transformer architecture.
method Neural scaling laws and task diversity for in-domain and out-of-domain generalization.
result Novel notion of task diversity for necessary and sufficient condition of generalization under task shifts.
Bayesian analysis reveals epistemic uncertainty as a key diagnostic for delayed generalization in in-context learning.
problem Delayed generalization in in-context learning from few examples.
method Bayesian perspective, modular arithmetic tasks, approximate Bayesian techniques, spectral mechanism analysis.
result Epistemic uncertainty collapses sharply when the model groks, indicating a practical diagnostic of generalization.
An app-based mHealth intervention uses reinforcement learning to send effective reminder notifications.
problem Designing an effective reinforcement learning algorithm for app-based mHealth interventions.
method Developed a reinforcement learning algorithm to send reminder notifications based on participant likelihood of app engagement.
result The algorithm improved app-based mHealth interventions by reducing participant burden and promoting behavior change.
Transformers enable in-context learning with guarantees for a wide range of tasks.
problem How to enable in-context learning with transformers for various tasks.
method Developed a universal approximation theory integrating Barron's function approximation with transformer capabilities.
result Transformers can approximate any target function with vanishingly small risk using a few in-context examples.
Unified Bayesian model explains in-context learning and activation steering in LLMs.
problem Understanding and controlling the behavior of large language models (LLMs) through prompts and activations.
method Developed a Bayesian model to explain and predict the effects of in-context learning and activation steering.
result Unified model predicts distinct phases and sudden shifts in LLM behavior, explaining prior empirical phenomena.
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.
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.
Looped Transformers improve robustness and expressivity in in-context learning for diverse tasks.
problem Improving robustness and expressivity in in-context learning for diverse tasks.
method Study in-context linear regression with diverse tasks, focusing on depth and looping.
result Looped Transformers exhibit similar expressive power and are provably robust under mild assumptions.
Transformers learn to solve modular arithmetic tasks by in-context learning and skill composition.
problem Understanding how large language models generalize to unseen tasks in modular arithmetic.
method Pre-training on a set of modular arithmetic tasks and evaluating out-of-distribution performance.
result Transformers require two transformer blocks for out-of-distribution generalization, and deeper models exhibit transient out-of-distribution performance.
Transformers learn rich in-context dependencies efficiently.
problem Understanding how transformers learn long-range dependencies efficiently.
method Approximation and dynamics analysis of induction head mechanisms.
result Abrupt transition from lazy to rich mechanisms during training.
Transformers converge linearly to optimal models for Gaussian mixtures classification.
problem Theoretical understanding of transformers' in-context classification.
method Gradient descent training of a single-layer transformer for Gaussian mixtures classification.
result Transformers converge linearly to globally optimal models for Gaussian mixtures classification.
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.
The paper proves how Transformers learn from context and generalize well.
problem Understanding how Transformers generalize from diverse tasks.
method Developed a statistical theory for in-context learning, separating risk into Bayes Gap and Posterior Variance.
result The Posterior Variance is task-independent, and the Bayes Gap decreases with more in-context examples.
The paper addresses adversarial robustness in in-context learning models.
problem Adversarial distribution shifts threaten the reliability of in-context learning models.
method A distributionally robust meta-learning framework is introduced to provide worst-case performance guarantees under Wasserstein-based distribution shifts.
result Model robustness scales with the square root of its capacity and is penalized by the square of the perturbation magnitude.
Paper analyzes Transformer learning dynamics, proving benign landscape for in-context learning.
problem Understanding how Transformers learn in context with nonlinear features.
method Mean-field and two-timescale analysis of Transformer dynamics, proving nonconvex but benign landscape.
result Proves mean-field dynamics avoid saddle points, leading to improved optimization.
We demystify attention patterns in multi-head softmax models for linear data.
problem Understanding the training dynamics and emergent patterns in multi-head softmax attention models.
method Extensive empirical experiments and rigorous theoretical analysis.
result Multi-head softmax attention models approximate a debiased gradient descent predictor, outperforming single-head attention and achieving near-Bayesian optimality.
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.
Adaptive reward models capture individual preferences from human feedback.
problem Learning a reward model that can be specialised to a user.
method Empirical risk minimisation and PAC bound analysis.
result Adaptive reward models benefit from the heterogeneity of user preferences.
Transformers learn algorithms for in-context learning with bounds and stability analysis.
problem Understanding and formalizing in-context learning as an algorithm learning problem.
method Formalizing ICL as a multitask learning problem, deriving generalization bounds, and analyzing stability.
result Transformers can implement near-optimal algorithms for classical regression tasks with i.i.d. and dynamic data.
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 to solve various tasks without explicit design.
problem Training models with minimal inductive bias.
method Meta-learning approach to train general-purpose in-context learning algorithms.
result Transformers can be meta-trained to solve a wide range of tasks.
The study provides precise asymptotic theory for in-context learning by Transformers.
problem Understanding the sample complexity, pretraining task diversity, and context length for successful in-context learning.
method An exactly solvable model of linear regression task by linear attention, deriving sharp asymptotics.
result Double-descent learning curve with increasing pretraining examples, phase transition between low and high task diversity regimes.
Multi-head attention outperforms single-head in in-context linear regression tasks.
problem Comparing performance of transformer with single-/multi-head attention in in-context learning.
method Theoretical analysis of performance of transformers with different attention mechanisms in linear regression tasks.
result Multi-head attention with a substantial embedding dimension outperforms single-head attention in in-context linear regression tasks.
Mamba efficiently learns low-dimensional targets in-context via feature extraction.
problem Learning low-dimensional targets in context for computational efficiency.
method Test-time feature learning of a single-index model using Mamba's pretrained linear-time sequence model.
result Mamba achieves efficient in-context learning of low-dimensional targets via feature extraction.