projection operator
Unsupervised Learning of 3D Structure from Images
Danilo Jimenez Rezende, S. M. Ali Eslami, Shakir Mohamed, Peter Battaglia, Max Jaderberg, Nicolas Heess
Neural Information Processing Systems http://nips.cc/
AFoundationModel forZero-shotLogicalQuery Reasoning
EPFO is the average of 9 query types with(,) operators, Negation is the average of 5 query types with the negation operator(). On average, a single ULTRAQUERY model outperforms the best baselines trained specifically on each dataset.
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
The proposed algorithm, termed ProjDiff, effectively harnesses the prior information and the denoising capability of a pre-trained diffusion model within the optimization framework.
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features
Md Enayat Ullah, Poorya Mianjy, Teodor Vanislavov Marinov, Raman Arora
Neural Information Processing Systems http://nips.cc/
An operator view of policy gradient methods
These techniques mainly fall in one of two categories: value-based methods [e.g.,
Structured Sparse Regression via Greedy Hard Thresholding
Prateek Jain, Nikhil Rao, Inderjit S. Dhillon
In this paper, we show that such NP-hard projections can not only be avoided by appealing to submodular optimization, but such methods come with strong theoretical guarantees even in the presence of poorly conditioned data (i.e. say when two features have
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features
Md Enayat Ullah, Poorya Mianjy, Teodor Vanislavov Marinov, Raman Arora
Neural Information Processing Systems http://nips.cc/
Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
Nayak, Anupam, Yang, Tong, Yagan, Osman, Joshi, Gauri, Chi, Yuejie
Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes to promote exploration (using uniform reference policy, known as entropy regularization). Beyond serving as a mere anchor, the reference policy can also be interpreted as encoding prior knowledge about good actions in the environment. In the context of alignment, recent game-theoretic approaches have leveraged KL regularization with pretrained language models as reference policies, achieving notable empirical success in self-play methods. Despite these advances, the theoretical benefits of KL regularization in game-theoretic settings remain poorly understood. In this work, we develop and analyze algorithms that provably achieve improved sample efficiency under KL regularization. We study both two-player zero-sum Matrix games and Markov games: for Matrix games, we propose OMG, an algorithm based on best response sampling with optimistic bonuses, and extend this idea to Markov games through the algorithm SOMG, which also uses best response sampling and a novel concept of superoptimistic bonuses. Both algorithms achieve a logarithmic regret in $T$ that scales inversely with the KL regularization strength $β$ in addition to the standard $\widetilde{\mathcal{O}}(\sqrt{T})$ regret independent of $β$ which is attained in both regularized and unregularized settings