Search Results for author:
Found 18 papers, 3 papers with code
Cross-Lingual Transfer with MAML on Trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+1
Score Normalization for a Faster Diffusion Exponential Integrator Sampler
As a simple fix, we propose to instead reparameterise the score (at inference) by dividing it by the average absolute value of previous score estimates at that time step collected from offline high NFE generations.
Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling
In this paper, we propose a diffusion model based channel sampling approach for rapidly synthesizing channel realizations from limited data.
Image generation with shortest path diffusion
We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring.
Sample Complexity of Kernel-Based Q-Learning
To the best of our knowledge, this is the first result showing a finite sample complexity under such a general model.
Delayed Feedback in Kernel Bandits
An abstraction of the problem can be formulated as a kernel based bandit problem (also known as Bayesian optimisation), where a learner aims at optimising a kernelized function through sequential noisy observations.
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Kernel-based models such as kernel ridge regression and Gaussian processes are ubiquitous in machine learning applications for regression and optimization.
Uniform Generalization Bounds for Overparameterized Neural Networks
As a byproduct of our results, we show the equivalence between the RKHS corresponding to the NT kernel and its counterpart corresponding to the Mat\'ern family of kernels, showing the NT kernels induce a very general class of models.
Optimal Order Simple Regret for Gaussian Process Bandits
Consider the sequential optimization of a continuous, possibly non-convex, and expensive to evaluate objective function $f$.
Natural continual learning: success is a journey, not (just) a destination
In contrast, artificial agents are prone to 'catastrophic forgetting' whereby performance on previous tasks deteriorates rapidly as new ones are acquired.
How to distribute data across tasks for meta-learning?
We show that: 1) If tasks are homogeneous, there is a uniform optimal allocation, whereby all tasks get the same amount of data; 2) At fixed budget, there is a trade-off between number of tasks and number of data points per task, with a unique solution for the optimum; 3) When trained separately, harder task should get more data, at the cost of a smaller number of tasks; 4) When training on a mixture of easy and hard tasks, more data should be allocated to easy tasks.
Meta-Learning with MAML on Trees
We show that TreeMAML improves the state of the art results for cross-lingual Natural Language Inference.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+2
Meta-learning with negative learning rates
We study the performance of MAML as a function of the learning rate of the inner loop, where zero learning rate implies that there is no inner loop.
Optimal allocation of data across training tasks in meta-learning
They are tested on benchmarks with a fixed number of data-points for each training task, and this number is usually arbitrary, for example, 5 instances per class in few-shot classification.
Model agnostic meta-learning on trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related, and sharing information between unrelated tasks might hurt performance.
Cyclic orthogonal convolutions for long-range integration of features
We propose a novel architecture that allows flexible information flow between features $z$ and locations $(x, y)$ across the entire image with a small number of layers.
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data
Here, we propose a new family of “dynamical” priors over trajectories, in the form of GP covariance functions that express a property shared by most dynamical systems: temporal non-reversibility.
Exact natural gradient in deep linear networks and its application to the nonlinear case
Stochastic gradient descent (SGD) remains the method of choice for deep learning, despite the limitations arising for ill-behaved objective functions.
