54 citations · 93 across the 4 of their papers we have counts for
4 papers
Deep Thinking by Markov Chain of Continuous Thoughts
Jiayu Liu, Zhenya Huang, Xuan Yang +6
Transformer-based models can perform complicated reasoning by generating reasoning paths token by token. While effective, this approach often requires generating thousands of token…
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
Tim G. J. Rudner, Cong Lu, Michael A. Osborne +2
KL-regularized reinforcement learning from expert demonstrations has proved successful in improving the sample efficiency of deep reinforcement learning algorithms, allowing them t…
Probabilistic symmetries and invariant neural networks
Benjamin Bloem-Reddy, Yee Whye Teh
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant un…
Hamiltonian Descent Methods
Chris J. Maddison, Daniel Paulin, Yee Whye Teh +2
We propose a family of optimization methods that achieve linear convergence using first-order gradient information and constant step sizes on a class of convex functions much large…