sec
Watermarking Autoregressive Image Generation
Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted the first such to watermark approach their by adapting outputs language at the tok model en level.
Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks
Anirvan Sengupta, Cengiz Pehlevan, Mariano Tepper, Alexander Genkin, Dmitri Chklovskii
Neural Information Processing Systems http://nips.cc/
The emergence of multiple retinal cell types through efficient coding of natural movies
Samuel Ocko, Jack Lindsey, Surya Ganguli, Stephane Deny
Neural Information Processing Systems http://nips.cc/
Faster Neural Networks Straight from JPEG
Lionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, Jason Yosinski
But could more performance be squeezed out of networks by using different input representations?
On Controllable Sparse Alternatives to Softmax
Anirban Laha, Saneem Ahmed Chemmengath, Priyanka Agrawal, Mitesh Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy
Converting an n-dimensional vector to a probability distribution over n objects isacommonly used component inmanymachine learning tasks likemulticlass classification,multilabelclassification,attentionmechanismsetc.
A Bayes-Sard Cubature Method
Toni Karvonen, Chris J. Oates, Simo Sarkka
Neural Information Processing Systems http://nips.cc/
Completing State Representations using Spectral Learning
Nan Jiang, Alex Kulesza, Satinder Singh
Neural Information Processing Systems http://nips.cc/
Temporal Regularization for Markov Decision Process
Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup
Yetinreinforcementlearning,duetothenatureofthe Bellman equation, there isanopportunity toalsoexploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization.
Exponentially Weighted Imitation Learning for Batched Historical Data
Qing Wang, Jiechao Xiong, Lei Han, peng sun, Han Liu, Tong Zhang
We consider deep policy learning with only batched historical trajectories. The main challenge of this problem is that the learner no longer has a simulator or "environment oracle" as in most reinforcement learning settings.
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama
Adversarial training [10, 16, 18], which injects adversarially perturbed dataintotraining data,isapromising approach. Many other heuristics have been developed to make neural networks insensitive against small perturbations on inputs.