Advances in Neural Information Processing Systems (NIPS)

By Hemant Tyagi, Bernd Gärtner, Andreas Krause. 2014

315 citations recorded by the source corpus.

Subfields: Large Language Models, Reinforcement Learning, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Large Language Models

In Reinforcement Learning

In Model Architectures

Citations in the corpus

Causal Models for Dynamical Systems (2020, background): “There are some works that have made first attempts to circumvent the difficulties of models using SDEs by looking at random differential equations [Bauer et al. 2017, Bongers and Mooij 2018, Abbati et al. 2019], which still allow including randomness directly into the causal structure.”
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models (2018, background): “However, current model-free reinforcement learning algorithms are quite expensive to train, which often limits their application to simulated domains [1], [2], [3], with a few exceptions [4], [5].”
Continual Learning with Adaptive Weights (CLAW) (2019, methodology): “In addition to the explicit replay form, some works have been based on generative replay (Thrun, 1996; Schmidhuber, 2013; Mocanu et al., 2016; Rebuffi et al., 2017; Kamra et al., 2017; Shin et al., 2017; van de Ven & Tolias, 2018; Wu et al., 2018).”
Fast ConvNets Using Group-Wise Brain Damage (2015, neutral): “This approach does not sparsify the convolutional kernel and is therefore different from the group-wise brain damage approach we suggest here.”
Discovering Attribute Shades of Meaning with the Crowd (2015, methodology): “Other approaches find within-category modes in order to perform better domain adaptation for object recognition (Hoffman et al, 2012; Gong et al, 2013; Xiong et al, 2014).”
On autoencoder scoring (2013, methodology): “The view of the autoencoder as a dynamical system was proposed by (Seung, 1998), who also demonstrated how de-noising as a learning criterion follows naturally from this perspective.”
Survey on reinforcement learning for language processing (2021, unknown): “2017), RankGAN (Lin et al.”
Predicting breast tumor proliferation from whole‐slide images: The TUPAC16 challenge (2018, background): “, 2009) Based on heuristic mapping of the color channels that highlights dark tumor areas AlexNet architecture (Krizhevsky et al., 2012) Heuristic thresholds for the number of detected mitotic figures in the ROIs”
Logistic Matrix Factorization for Implicit Feedback Data (2014, background): “Probabilistic approaches to collaborative filtering attempt to encode the probability of a user choosing to interact with an item.”
Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation (2020, methodology): “We adopt the gradient penalty setup as proposed in Gulrajani et al. (2017) for more robust training.”
Discovering Interpretable Representations for Both Deep Generative and Discriminative Models (2018, background): “Several works that followed (Kulkarni et al., 2015; Hsu et al., 2017; Chen et al., 2016; Siddharth et al., 2017; Higgins et al., 2017) instead jointly optimize the latent representation for both reconstruction fidelity and interpretability.”
Direct Validation of the Information Bottleneck Principle for Deep Nets (2019, background): “This is similar to the principle underlying adversarial training [7].”