20 results for “dictionary learning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper proposes Consistent Sparse Dictionary Learning (ConSDL) to improve the reliability and reproducibility of sparse autoencoders.
The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…
This paper shows that sub-dictionaries sampled from a coherent dictionary using a coherence rejective Poisson sampling model are well-conditioned with high probability, as long as their expected size…
A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…
This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.
The paper introduces Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning that achieves the standard inductive rate and matches the transductive minima…
The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…
This paper improves the sample complexity of learning robust predictors to adversarial examples using a simple algorithm that combines bagging and robust empirical risk minimization.
This paper introduces a new data-adaptive, learnt transform for sparse signal representation.
This paper proposes a compression scheme for transmitting sparse local updates in distributed learning systems, and provides a converse based on f-divergence to characterize the communication-accuracy…
Liad Erez, Fan Chen, Alon Cohen, Tomer Koren +3 more
The paper analyzes the sample complexity of contextual bandits in the $s$-sparse setting, achieving optimal sample bounds for identifying an $\epsilon$-optimal policy.
The paper studies the problem of learning a drifting concept in the presence of Massart noise and provides an efficient learner with improved error rate for margin-separable linear classifiers.
This paper proposes a scheme to optimize model sparsity in neural sparse retrieval using adaptive strategies.
Jaeeun Baik, Ui-Hyeop Shin, Jiwoon Lee, Woocheol Jeong +1 more
The paper proposes DASH, a self-distillation framework that improves ASR robustness in noisy environments by learning clean-noisy consistency from paired views.
This paper studies how transformers exploit task-relevant structure in geometrically heterogeneous data and provides a new estimator and generalization bound for in-context learning.
Boqian Wu, Qiao Xiao, Patrik Okanovic, Tomasz Sternal +5 more
This paper introduces a new scaling law for sparse language models trained with limited data, demonstrating that sparsity can significantly improve performance and delay data saturation during multi-e…