Survey and compare PAC-Bayes bounds for bandit problems.
problem Designing and evaluating bandit algorithms with strong performance guarantees.
method PAC-Bayes bounds applied to bandit problems.
result PAC-Bayes bounds useful for offline bandit algorithms, but loose for online algorithms.
New PAC-Bayes bounds for unbounded loss functions.
problem Generalization bounds for learning problems with unbounded loss functions.
method Introducing HYPE, a new notion for loss range, and deriving a novel PAC-Bayesian generalization bound.
result PAC-Bayes framework extended to unbounded loss functions.
Paper analyzes error exponent in agnostic PAC learning.
problem Analyzing performance of agnostic PAC learning.
method Using error exponent from Information Theory to analyze PAC learning.
result Improved distribution-dependent error exponent for agnostic learning.
Paper refines PAC-Bayes bounds for bandit problems.
problem Improving probabilistic bounds for off-policy learning.
method Optimizes PAC-Bayesian bounds using a new parameter optimization approach.
result Provides two parameter-free PAC-Bayes bounds that nearly match optimal rates.
New bounds show covariate shift doesn't make PAC learning impossible.
problem Learning under different distributions with same labels.
method Recontextualizing PAC learning bounds for covariate shift.
result PAC learnable concepts are still learnable under covariate shift with polynomial sample increase.
Efficient PAC learning for contrastive linear representations is achieved.
problem Efficient PAC learning for contrastive linear representations.
method Relaxing the problem to a semi-definite program and using Rademacher complexity.
result First efficient PAC learning algorithm for contrastive learning.
Paper proposes efficient algorithms for bandit problems with costly sampling.
problem Maximizing expectation function over a finite set with high sampling cost.
method Proposes naive and adaptive stochastic bandit algorithms for PAC solution.
result Adaptive algorithm outperforms naive in terms of number of samples.
New PAC-Bayesian bounds for online learning with data streams.
problem Challenges of traditional PAC-Bayesian bounds in dynamic data collection.
method Developed new PAC-Bayesian bounds in online learning framework, using updated regret definition and batch-to-online conversion.
result PAC-Bayesian bounds hold for online learning with dependent data and non-convex losses.
Algorithm constructs confidence sets for deep neural networks with PAC guarantees.
problem Ensuring reliable predictions for deep neural networks with high confidence.
method Combines calibrated prediction and learning theory bounds.
result Constructs PAC confidence sets for various deep models.
PAC-Bayesian theory applied to learning optimization algorithms with generalization guarantees.
problem Learning optimization algorithms with provable generalization guarantees and explicit trade-offs.
method PAC-Bayes theory applied to learning-to-optimize, reformulating the learning procedure into a one-dimensional minimization problem.
result Learned optimization algorithms outperform deterministic worst-case analysis algorithms, even in the limit case of guaranteed convergence.
New PAC bound for meta-learning improves generalization guarantees.
problem Provide strong generalization guarantees in meta-learning.
method PAC-Bayes and uniform stability frameworks applied to gradient-based meta-learning.
result Derives a tighter PAC bound for gradient-based meta-learning.
This work establishes a new upper bound on the number of samples sufficient for PAC learning in the realizable case. The bound matches known lower bounds up to numerical constant factors. This solves a long-standing open problem on the sample complexity of PAC learning. The technique and analysis build on a recent brea…
Introduces PAC-Bayes bounds for understanding learning procedures.
problem Understanding the generalization ability of learning procedures.
method PAC-Bayesian bounds and their applications to neural networks.
result Simplified version of localization technique described.
Paper improves PAC-Bayes bounds using a better-than-KL divergence.
problem Estimating the generalization error of stochastic algorithms.
method Developed new PAC-Bayes bounds with a novel divergence.
result Achieved strictly tighter bounds than the KL divergence.
Learn conditional averages in PAC framework for better predictions.
problem Learning average labels over neighborhoods in unknown concept class.
method Characterization of learnability using combinatorial parameters.
result Complete characterization and sample complexity bounds.
PACOH improves meta-learning with theoretical guarantees and practical efficiency.
problem Meta-learning's generalization to unseen tasks is poorly understood, especially with limited meta-training tasks.
method PAC-Bayesian framework for deriving generalization bounds and developing PAC-optimal meta-learning algorithms.
result PACOH yields state-of-the-art performance in predictive accuracy and uncertainty estimation.
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless …
PAC-Bayesian matrix completion with a spectral scaled Student prior offers efficient inference.
problem Matrix completion with underlying low-rank structure.
method Spectral scaled Student prior and PAC-Bayesian bounds.
result Minimax-optimal oracle inequality for model misspecification and general sampling distribution.
New algorithm FLUTE achieves uniform-PAC convergence in RL with linear approx.
problem RL with linear function approximation lacks uniform-PAC guarantees.
method FLUTE algorithm with minimax value function estimator and multi-level partition scheme.
result Uniform-PAC convergence to optimal policy with high probability.
Develops a theory to make learning solutions fair and safe.
problem Ensuring learning solutions are unbiased and safe in critical applications.
method Generates a generalization theory based on PAC learning framework, introduces constrained learning algorithm.
result Proves that constrained learning is as learnable as unconstrained learning, provides practical algorithm.
Paper proves L2 regression can learn k-juntas without distributional assumptions.
problem Learning k-juntas using L2 regression without distributional restrictions.
method L2 polynomial regression and minimum mean square estimation (MMSE).
result Agnostic PAC learning of k-juntas using L2 polynomial regression.
This work uses PAC-Bayes for structured prediction with ILE, yielding insights and algorithms.
problem Structured prediction with interdependent outputs and implicit loss embeddings.
method PAC-Bayes perspective applied to ILE framework, deriving generalization bounds and learning algorithms.
result Two learning algorithms derived from PAC-Bayes bounds, analyzed and implemented.
New algorithm constructs PAC prediction sets for meta-learning.
problem Uncertainty quantification in safety-critical systems.
method Proposes a novel algorithm to construct PAC prediction sets.
result Prediction sets satisfy a PAC guarantee with high probability over future tasks.
Study computable multiclass learning within PAC framework.
problem Computable multiclass learnability in finite label space.
method Proposed computable version of Natarajan dimension and generalized to distinguishers.
result Characterizes CPAC learnability for certain dimensions and embeddings.
Paper tightens PAC-Bayes bounds using coin-betting for better estimates.
problem Estimating mean of random elements with possibly S-dependent parameters.
method Refined PAC-Bayes proof strategy based on coin-betting framework.
result Derives tighter concentration inequalities for all sample sizes.
We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Ho gen ([7]) have shown that this class is PAC-learnable by reducing it to …
Theory vs practice in machine learning, showing practical limitations.
problem Applying machine learning theory to real-world business problems.
method Formalized and compared applied learning and agnostic PAC learning.
result Theoretical learning requires impractically large datasets.
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by expectations of the same functions of independent Bernoulli random variables. This …
PAC-Bayesian analysis improves lifelong learning in multi-armed bandits.
problem Improving lifelong learning in multi-armed bandits.
method PAC-Bayesian analysis for deriving lower bounds and proposing lifelong learning algorithms.
result Proposed algorithms outperform baseline methods in lifelong multi-armed bandit problems.
Paper bounds PAC RL sample complexity in deterministic MDPs.
problem Identify ε-optimal policy with high probability.
method Proposes nearly matching upper and lower bounds on sample complexity, introduces deterministic return gap, uses graph-theoretical concepts and maximum-coverage exploration.
result First nearly matching upper and lower bounds on sample complexity for PAC RL in deterministic MDPs.
PAC-Bayesian theory applied to data-dependent hypothesis sets yields uniform generalization bounds.
problem Proving uniform generalization bounds for data-dependent hypothesis sets.
method Applying PAC-Bayesian framework on 'random sets' and considering data-dependent hypothesis sets.
result Data-dependent uniform generalization bounds are proven, providing tighter and unified results.
Learning feasibility is undecidable in PAC-learning.
problem Deciding the feasibility of learning a mapping between data and labels.
method Investigating the existence of a test for PAC-learnability.
result No test for PAC-learnability exists, showing undecidability.
Paper derives an error bound for stochastic LTI systems.
problem Stochastic LTI systems with inputs in control engineering and econometrics.
method PAC-Bayesian-Like error bound derivation.
result Derived an error bound for stochastic LTI systems.
Improved PAC learning algorithm for multiclass classification with bandit feedback.
problem Efficiently learning multiclass classification with limited feedback.
method Novel algorithm using stochastic optimization and Frank-Wolfe updates.
result Improved sample complexity bounds for multiclass PAC learning.
New findings on PAC learning and marginal distribution estimation.
problem Understanding how PAC learning relates to marginal distribution estimation under distributional constraints.
method Revisited the connection between PAC learning, uniform convergence, and density estimation, considering a known family of marginal distributions.
result PAC learning is sandwiched between two refined models of density estimation, differing only in whether the learner knows the set of well-estimated events in H.
Paper extends PAC-Bayesian theory using shifted Rademacher processes.
problem Improving PAC-Bayesian bounds for fast rates.
method Using shifted Rademacher processes to match Catoni's bounds and derive new fast-rate bounds.
result New fast-rate PAC-Bayes bounds derived in terms of empirical risk surface flatness.
New algorithms achieve uniform-PAC guarantees for RL with bounded eluder dimension.
problem Achieving strong performance guarantees in reinforcement learning.
method Proposes algorithms for nonlinear bandits and model-based episodic RL with a bounded eluder dimension.
result Achieves uniform-PAC sample complexity that matches state-of-the-art regret bounds or sample complexity guarantees.
New method optimises learning via surrogate PAC-Bayes bounds.
problem Computational intractability of optimising generalisation bounds.
method Iteratively optimising surrogate training objectives derived from PAC-Bayes bounds.
result Iteratively optimising surrogates implies optimising original generalisation bounds.
Survey on PAC-Bayesian learning for machine learning.
problem Generalisation properties and flexibility of Bayesian learning.
method PAC-Bayesian framework and its theoretical developments.
result Survey of PAC-Bayesian learning.
PAC-Bayesian bounds for MLPs with cross entropy loss validated.
problem Generalization bounds for MLPs with cross entropy loss.
method Introduced probabilistic explanations and proved PAC-Bayesian bounds using ELBO.
result MLPs with cross entropy loss inherently guarantee PAC-Bayesian generalization bounds.
New inequality for ternary variables improves on existing measures.
problem Analyzing excess losses and weighted majority votes with ternary random variables.
method Developed a split-kl inequality and its PAC-Bayes extension.
result Outperforms existing inequalities in certain regimes.
The paper studies ranking algorithms from pairwise and listwise comparisons, deriving lower bounds and optimal algorithms.
problem Designing efficient ranking algorithms from pairwise and listwise comparisons.
method Deriving lower bounds and proposing optimal algorithms for top-k and total ranking problems.
result The proposed algorithms match the derived lower bounds and are optimal up to a logarithmic factor.
Local regularization fails in transductive learning for some multiclass problems.
problem Whether local regularization can learn all transductive multiclass problems.
method Provided a negative answer by exhibiting a specific multiclass problem.
result Local regularization cannot learn all transductive multiclass problems.
New algorithm reduces contextual bandit identification to argmax calls.
problem Best-arm identification in stochastic contextual bandits.
method Instance-optimal PAC algorithm using argmax oracle calls.
result First instance-dependent PAC sample complexity for contextual bandits.
New algorithm tackles constrained Markov decision processes with peak constraints.
problem Optimizing dynamic systems with peak constraints.
method Model-free algorithm converting PCMDP to unconstrained problem, applying Q-learning.
result Algorithm achieves (ε,p)-PAC policy under certain conditions. Unified derivation of PAC-Bayes and MI bounds for general VC classes with fast rates.
problem Generalization bounds for machine learning models with VC classes.
method Unified derivation of conditional PAC-Bayesian and mutual information bounds, including MAC-Bayesian bounds.
result Nontrivial bounds for general VC classes and faster rates for specific conditions.
Study shows mean-field approximation fails to improve PAC-Bayes bounds for neural networks.
problem Understanding why overparametrized neural networks achieve low risk and zero empirical risk.
method Optimized PAC-Bayes bounds using variational inference (VI), investigating mean-field approximation.
result Mean-field approximation does not provide significant improvements in PAC-Bayes bounds for neural networks.
PAC-Wrap provides provable guarantees for semi-supervised anomaly detection.
problem Ensuring reliable anomaly detection in safety-critical applications.
method PAC-Wrap wraps around existing anomaly detection methods to provide PAC guarantees.
result PAC-Wrap effectively provides rigorous guarantees for various anomaly detectors.