Search Results for author:
Found 18 papers, 10 papers with code
C3: High-performance and low-complexity neural compression from a single image or video
On the UVG video benchmark, we match the RD performance of the Video Compression Transformer (Mentzer et al.), a well-established neural video codec, with less than 5k MACs/pixel for decoding.
Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
This work studies a central extremal graph theory problem inspired by a 1975 conjecture of Erd\H{o}s, which aims to find graphs with a given size (number of nodes) that maximize the number of edges without having 3- or 4-cycles.
Spatial Functa: Scaling Functa to ImageNet Classification and Generation
Neural fields, also known as implicit neural representations, have emerged as a powerful means to represent complex signals of various modalities.
When Does Re-initialization Work?
However, when deployed alongside other carefully tuned regularization techniques, re-initialization methods offer little to no added benefit for generalization, although optimal generalization performance becomes less sensitive to the choice of learning rate and weight decay hyperparameters.
Pre-training via Denoising for Molecular Property Prediction
Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks.
Learning Instance-Specific Augmentations by Capturing Local Invariances
We introduce InstaAug, a method for automatically learning input-specific augmentations from data.
From data to functa: Your data point is a function and you can treat it like one
A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location.
Group Equivariant Subsampling
We use these layers to construct group equivariant autoencoders (GAEs) that allow us to learn low-dimensional equivariant representations.
LieTransformer: Equivariant self-attention for Lie Groups
Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency through principled parameter sharing.
Conditional Set Generation with Transformers
An example of such a generator is the DeepSet Prediction Network (DSPN).
The Lipschitz Constant of Self-Attention
Lipschitz constants of neural networks have been explored in various contexts in deep learning, such as provable adversarial robustness, estimating Wasserstein distance, stabilising training of GANs, and formulating invertible neural networks.
MetaFun: Meta-Learning with Iterative Functional Updates
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one.
Meta-Learning surrogate models for sequential decision making
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning.
Attentive Neural Processes
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions.
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
It can reliably discover and track objects throughout the sequence of frames, and can also generate future frames conditioning on the current frame, thereby simulating expected motion of objects.
Disentangling by Factorising
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation.
Scaling up the Automatic Statistician: Scalable Structure Discovery using Gaussian Processes
Automating statistical modelling is a challenging problem in artificial intelligence.
Collaborative Filtering with Side Information: a Gaussian Process Perspective
We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression.
