paper-with-me

홈 › Papers

The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR

2026-02-02 · Israel Adewuyi, Solomon Okibe, Vladmir Ivanov arxiv

The Lottery Ticket Hypothesis demonstrated that sparse subnetworks can match full-model performance, suggesting parameter redundancy. Meanwhile, in Reinforcement Learning with Verifiable Rewards (RLVR), recent work has shown that updates concentrate on a sparse subset of parameters, which further lends evidence to this underlying redundancy. We study the simplest possible way to exploit this redundancy: training only a randomly selected subset of parameters at extreme sparsities. Empirically, we find that training just 1\% of parameters matches or exceeds full-parameter RLVR finetuning across 3 models and 2 task domains. Moreover, different random masks show minimal overlap ($\leq 0.005$ Jaccard similarity) and yet all succeed, suggesting pretrained models contain many viable sparse subnetworks rather than one privileged set. We term this the Multiple Ticket Hypothesis. We explain this phenomenon through the implicit per-step KL constraint in RLVR, which restricts updates to a low-dimensional subspace, enabling arbitrary sparse masks to succeed.

📄 PDF Abstract BibTeX arXiv:2602.01599

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Dual Lottery Ticket Hypothesis

2022-03-08 · ICLR 2022 4 · Yue Bai, Huan Wang, Zhiqiang Tao, Kunpeng Li 외

Fully exploiting the learning capacity of neural networks requires overparameterized dense networks. On the other side, directly training sparse neural networks typically results in unsatisfactory performance. Lottery Ti…

Evaluating Lottery Tickets Under Distributional Shifts

2019-10-28 · WS 2019 11 · Shrey Desai, Hongyuan Zhan, Ahmed Aly

The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initializa…

Inductive Bias

On the Sparsity of the Strong Lottery Ticket Hypothesis

2024-10-18 · Emanuele Natale, Davide Ferre', Giordano Giambartolomei, Frédéric Giroire 외

Considerable research efforts have recently been made to show that a random neural network $N$ contains subnetworks capable of accurately approximating any given neural network that is sufficiently smaller than $N$, with…

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

2018-03-09 · ICLR 2019 5 · Jonathan Frankle, Michael Carbin

Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. Howev…

Network Pruning

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

2022-05-31 · Daiki Chijiwa, Shin'ya Yamaguchi, Atsutoshi Kumagai, Yasutoshi Ida

Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized NNs can easily overfit to such small dat…

Few-Shot LearningMeta-Learning