paper-with-me

홈 › Papers

On the Learnability of Deep Random Networks

2019-04-08 · Abhimanyu Das, Sreenivas Gollapudi, Ravi Kumar, Rina Panigrahy

In this paper we study the learnability of deep random networks from both theoretical and practical points of view. On the theoretical front, we show that the learnability of random deep networks with sign activation drops exponentially with its depth. On the practical front, we find that the learnability drops sharply with depth even with the state-of-the-art training methods, suggesting that our stylized theoretical results are closer to reality.

📄 PDF Abstract BibTeX arXiv:1904.03866

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From learnable objects to learnable random objects

2025-04-01 · Aaron Anderson, Michael Benedikt

We consider the relationship between learnability of a "base class" of functions on a set $X$, and learnability of a class of statistical functions derived from the base class. For example, we refine results showing that…

PAC learning

Online Learning with Set-Valued Feedback

2023-06-09 · Vinod Raman, Unique Subedi, Ambuj Tewari

We study a variant of online multiclass classification where the learner predicts a single label but receives a \textit{set of labels} as feedback. In this model, the learner is penalized for not outputting a label conta…

On statistical learning of graphs

2025-07-17 · Vittorio Cipriani, Valentino Delle Rose, Luca San Mauro, Giovanni Solda arxiv

We study PAC and online learnability of hypothesis classes formed by copies of a countably infinite graph G, where each copy is induced by permuting G's vertices. This corresponds to learning a graph's labeling, knowing …

Learnability of Learned Neural Networks

2018-01-01 · ICLR 2018 1 · Rahul Anand Sharma, Navin Goyal, Monojit Choudhury, Praneeth Netrapalli

This paper explores the simplicity of learned neural networks under various settings: learned on real vs random data, varying size/architecture and using large minibatch size vs small minibatch size. The notion of simpli…

On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms

2020-06-17 · Adam Sutton, Nello Cristianini

Word Embeddings are used widely in multiple Natural Language Processing (NLP) applications. They are coordinates associated with each word in a dictionary, inferred from statistical properties of these words in a large c…

Two-sample testingWord Embeddings