33 citations · 42 across the 5 of their papers we have counts for
11 papers
Experimental Design Networks: A Paradigm for Serving Heterogeneous Learners under Networking Constraints
Yuezhou Liu, Yuanyuan Li, Lili Su +2
Significant advances in edge computing capabilities enable learning to occur at geographically diverse locations. In general, the training data needed in those learning tasks are n…
The Power of Random Symmetry-Breaking in Nakamoto Consensus
Lili Su, Quanquan C. Liu, Neha Narula
Nakamoto consensus underlies the security of many of the world's largest cryptocurrencies, such as Bitcoin and Ethereum. Common lore is that Nakamoto consensus only achieves consis…
On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
Lili Su, Pengkun Yang
We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study…
Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits
Lili Su, Chia-Jung Chang, Nancy Lynch
Winner-Take-All (WTA) refers to the neural operation that selects a (typically small) group of neurons from a large neuron pool. It is conjectured to underlie many of the brain's f…
Distributed Learning with Adversarial Agents Under Relaxed Network Condition
Pooja Vyavahare, Lili Su, Nitin H. Vaidya
This work studies the problem of non-Bayesian learning over multi-agent network when there are some adversarial (faulty) agents in the network. At each time step, each non-faulty a…
Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory
Lili Su, Martin Zubeldia, Nancy Lynch
We consider multi-armed bandit problems in social groups wherein each individual has bounded memory and shares the common goal of learning the best arm/option. We say an individual…