1.2k citations · 2.7k across the 112 of their papers we have counts for
15 papers · 1 filter
Accelerated Algorithm for Sparse Regularized Partial Optimal Transport
Khoa Nguyen, Dung T. Nguyen, Thong Huynh +4
Partial Optimal Transport (POT) extends the classical optimal transport problem by relaxing the strict mass conservation constraint, enabling its use in a wide range of real-world…
Sparsely Supervised Diffusion
Wenshuai Zhao, Zhiyuan Li, Yi Zhao +5
Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent generation, arguably due to the inher…
Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
Yi Zhao, Aidan Scannell, Wenshuai Zhao +7
Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online…
Optimistic Multi-Agent Policy Gradient
Wenshuai Zhao, Yi Zhao, Zhiyuan Li +2
*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior…
Simplified Temporal Consistency Reinforcement Learning
Yi Zhao, Wenshuai Zhao, Rinu Boney +2
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficienc…
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective
Yingtian Zou, Vikas Verma, Sarthak Mittal +6
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels.…
Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning
Yi Zhao, Rinu Boney, Alexander Ilin +2
Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the qua…
Disentangling Model Multiplicity in Deep Learning
Ari Heljakka, Martin Trapp, Juho Kannala +1
Model multiplicity is a well-known but poorly understood phenomenon that undermines the generalisation guarantees of machine learning models. It appears when two models with simila…
Learning of feature points without additional supervision improves reinforcement learning from images
Rinu Boney, Alexander Ilin, Juho Kannala
In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene. This information can be represented using feature poin…
Deep Automodulators
Ari Heljakka, Yuxin Hou, Juho Kannala +1
We introduce a new category of generative autoencoders called automodulators. These networks can faithfully reproduce individual real-world input images like regular autoencoders,…
Regularizing Model-Based Planning with Energy-Based Models
Rinu Boney, Juho Kannala, Alexander Ilin
Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional d…
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
Vikas Verma, Meng Qu, Kenji Kawaguchi +4
We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly wit…
Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders
Ari Heljakka, Arno Solin, Juho Kannala
We present a generative autoencoder that provides fast encoding, faithful reconstructions (eg. retaining the identity of a face), sharp generated/reconstructed samples in high reso…
Regularizing Trajectory Optimization with Denoising Autoencoders
Rinu Boney, Norman Di Palo, Mathias Berglund +4
Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting ina…
Pioneer Networks: Progressively Growing Generative Autoencoder
Ari Heljakka, Arno Solin, Juho Kannala
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from th…