Related papers: Optimally compressing VC classes

Related papers

VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression [52.23010472235226]
Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference and overhead latency.<n>We propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor.
arXiv Detail & Related papers (2026-07-14T13:21:36Z)
PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting [46.089126569274676]
We study the problem of multiclass PAC learning with bandit feedback in the realizable setting.<n>In this framework, there is an unknown data distribution over an instance space $mathcalX$ and a label space $mathcalY$.<n>We provide a general characterization of the optimal sample of this problem, sharp for every concept class up to complexity.
arXiv Detail & Related papers (2026-05-25T10:35:16Z)
Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale [54.65053906803857]
We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability.<n>Our main result establishes a scale-sensitive generalization of the fundamental theorem of PAC learning.<n>We also highlight several open questions on quantitative sample complexity and evaluability.
arXiv Detail & Related papers (2026-05-13T15:41:30Z)
An $\ ilde{O}$ptimal Differentially Private Learner for Concept Classes with VC Dimension 1 [4.834749573193387]
We present the first nearly optimal differentially private PAC learner for any concept class with VC dimension 1 and Littlestone dimension achieves $d$.<n>Our algorithm the sample complexity of $tildeO_varepsilon,delta,alpha,delta(log* d)$, nearly matching the lower bound of $Omega(log* d)$ proved by Alon et al.<n>Prior to our work, the best known upper bound is $tildeO(VCcdot d5)$ for general VC classes, as shown by
arXiv Detail & Related papers (2025-05-10T09:51:25Z)
CODA: Repurposing Continuous VAEs for Discrete Tokenization [52.58960429582813]
textbfCODA(textbfCOntinuous-to-textbfDiscrete textbfAdaptation) is a framework that decouples compression and discretization. Our approach achieves a remarkable codebook utilization of 100% and notable reconstruction FID (rFID) of $mathbf0.43$ and $mathbf1.34$ for $8 times$ and $16 times$ compression on ImageNet 256$times$ 256 benchmark.
arXiv Detail & Related papers (2025-03-22T12:59:00Z)
Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback [60.610120215789976]
We show that when a pure strategy Nash equilibrium exists, $c$ becomes zero, leading to an optimal instance-dependent regret bound. Our algorithm also enjoys last-iterate convergence and can identify the pure strategy Nash equilibrium with near-optimal sample.
arXiv Detail & Related papers (2025-02-24T20:20:06Z)
Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles [49.65811277223873]
Style-Compress is a lightweight framework that adapts a smaller language model to compress prompts for a larger model on a new task without additional training. Our approach iteratively generates and selects effective compressed prompts as task-specific demonstrations through style variation and in-context learning. Style-Compress outperforms two baseline compression models in four tasks: original prompt reconstruction, text summarization, multi-hop QA, and CoT reasoning.
arXiv Detail & Related papers (2024-10-17T21:35:49Z)
Sample Compression Scheme Reductions [17.389446817000945]
We present novel reductions from sample compression schemes in multiclass classification, regression, and adversarially robust learning settings. We establish similar results for adversarially robust learning and also provide an example of a concept class that is robustly learnable but has no bounded-size compression scheme.
arXiv Detail & Related papers (2024-10-16T20:14:02Z)
The Sample Complexity of Smooth Boosting and the Tightness of the Hardcore Theorem [53.446980306786095]
Smooth boosters generate distributions that do not place too much weight on any given example. Originally introduced for their noise-tolerant properties, such boosters have also found applications in differential privacy, mildly, and quantum learning theory.
arXiv Detail & Related papers (2024-09-17T23:09:25Z)
Fast Rates for Bandit PAC Multiclass Classification [73.17969992976501]
We study multiclass PAC learning with bandit feedback, where inputs are classified into one of $K$ possible labels and feedback is limited to whether or not the predicted labels are correct. Our main contribution is in designing a novel learning algorithm for the agnostic $(varepsilon,delta)$PAC version of the problem.
arXiv Detail & Related papers (2024-06-18T08:54:04Z)
Dual VC Dimension Obstructs Sample Compression by Embeddings [25.63430474763066]
This work studies embedding of arbitrary VC classes in well-behaved VC classes, focusing particularly on extremal classes. We prove that for every $d$ there is a class with VC dimension $d$ that cannot be embedded in any extremal class of VC dimension smaller than exponential in $d$. This result has an important implication in learning theory, as it reveals a fundamental limitation of one of the most extensively studied approaches to tackling the long-standing sample compression conjecture.
arXiv Detail & Related papers (2024-05-27T12:38:25Z)
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs [56.237917407785545]
We consider the problem of learning an $varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.
arXiv Detail & Related papers (2024-05-10T09:58:47Z)
A Labelled Sample Compression Scheme of Size at Most Quadratic in the VC Dimension [6.522952386973185]
This paper presents a construction of a proper and stable labelled sample compression scheme of size $O(VCD2)$ for any finite concept class.
arXiv Detail & Related papers (2022-12-24T01:56:02Z)
Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes [16.684376456880642]
We show that all classes of VC dimension $d$ admit unlabelled compression schemes of size $O(d)$. We also prove that all intersection-closed classes with VC dimension $d$ admit unlabelled compression schemes of size at most $11d$.
arXiv Detail & Related papers (2022-10-11T13:54:41Z)
Sample-efficient proper PAC learning with approximate differential privacy [51.09425023771246]
We prove that the sample complexity of properly learning a class of Littlestone dimension $d$ with approximate differential privacy is $tilde O(d6)$, ignoring privacy and accuracy parameters. This result answers a question of Bun et al. (FOCS 2020) by improving upon their upper bound of $2O(d)$ on the sample complexity.
arXiv Detail & Related papers (2020-12-07T18:17:46Z)
Private Query Release Assisted by Public Data [96.6174729958211]
We study the problem of differentially private query release assisted by access to public data. We show that we can solve the problem for any query class $mathcalH$ of finite VC-dimension using only $d/alpha$ public samples and $sqrtpd3/2/alpha2$ private samples.
arXiv Detail & Related papers (2020-04-23T02:46:37Z)
Agnostic Sample Compression Schemes for Regression [30.539063844697772]
We show that for every other $ell_p$ loss, $pin (1,infty)$, there does not exist an exact compression scheme of bounded size. For $ell$ loss, does every function class admit an approximate compression scheme of size in the fat-shattering dimension?
arXiv Detail & Related papers (2018-10-03T11:46:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.