Search Results for author:
Found 58 papers, 15 papers with code
Incremental Sequence Classification with Temporal Consistency
We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed.
Towards Training One-Step Diffusion Models Without Distillation
Recent advances in one-step generative models typically follow a two-stage process: first training a teacher diffusion model and then distilling it into a one-step student model.
Training Neural Samplers with Reverse Diffusive KL Divergence
To address this, we propose to minimize the reverse KL along diffusion trajectories of both model and target densities.
RotRNN: Modelling Long Sequences with Rotations
Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks.
Improving Probabilistic Diffusion Models With Optimal Covariance Matching
The probabilistic diffusion model has become highly effective across various domains.
Latte: Latent Attention for Linear Time Transformers
The time complexity of the standard attention mechanism in transformers scales quadratically with sequence length.
Active Preference Learning for Large Language Models
A key consideration for aligning these models is how to most effectively use human resources, or model resources in the case where LLMs themselves are used as oracles.
Diffusive Gibbs Sampling
The inadequate mixing of conventional Markov Chain Monte Carlo (MCMC) methods for multi-modal distributions presents a significant challenge in practical applications such as Bayesian inference and molecular dynamics.
CenTime: Event-Conditional Modelling of Censoring in Survival Analysis
We demonstrate that our approach forms a consistent estimator for the event model parameters, even in the absence of uncensored data.
Moment Matching Denoising Gibbs Sampling
Energy-Based Models (EBMs) offer a versatile framework for modeling complex data distributions.
Generalized Multiple Intent Conditioned Slot Filling
Natural language understanding includes the tasks of intent detection (identifying a user's objectives) and slot filling (extracting the entities relevant to those objectives).
A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
The Cox neural network can achieve an IPCW C-index of 0. 75 on the internal dataset and 0. 69 on an external dataset.
Smoothed Q-learning
In Reinforcement Learning the Q-learning algorithm provably converges to the optimal solution.
Towards Healing the Blindness of Score Matching
Score-based divergences have been widely used in machine learning and statistics applications.
Integrated Weak Learning
We introduce a label model that can learn to aggregate weak supervision sources differently for different datapoints and takes into consideration the performance of the end-model during training.
Improving VAE-based Representation Learning
Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images.
Generalization Gap in Amortized Inference
The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression.
Survival Analysis for Idiopathic Pulmonary Fibrosis using CT Images and Incomplete Clinical Data
To this end, we propose a probabilistic model that captures the dependencies between the observed clinical variables and imputes missing ones.
Parallel Neural Local Lossless Compression
The recently proposed Neural Local Lossless Compression (NeLLoC), which is based on a local autoregressive model, has achieved state-of-the-art (SOTA) out-of-distribution (OOD) generalization performance in the image compression task.
Adaptive Optimization with Examplewise Gradients
We propose a new, more general approach to the design of stochastic gradient-based optimization methods for machine learning.
Sample Efficient Model Evaluation
Labelling data is a major practical bottleneck in training and testing classifiers.
Locally-Contextual Nonlinear CRFs for Sequence Labeling
Linear chain conditional random fields (CRFs) combined with contextual word embeddings have achieved state of the art performance on sequence labeling tasks.
Solipsistic Reinforcement Learning
We introduce a new model-based reinforcement learning framework that aims to tackle environments with high dimensional state spaces.
Model-based Reinforcement Learning
reinforcement-learning
+2
{Learning disentangled representations with the Wasserstein Autoencoder
We further study the trade off between disentanglement and reconstruction on more-difficult data sets with unknown generative factors, where we expect improved reconstructions due to the flexibility of the WAE paradigm.
Efficiently labelling sequences using semi-supervised active learning
However, active learning methods usually use supervised training and ignore the data points which have not yet been labelled.
Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
In this work we show, for the first time, that we can successfully train generative models which utilize binary neural networks.
Representation Learning for High-Dimensional Data Collection under Local Differential Privacy
In this work, our contributions are two-fold: first, by adapting state-of-the-art techniques from representation learning, we introduce a novel approach to learning LDP mechanisms.
Learning disentangled representations with the Wasserstein Autoencoder
We further study the trade off between disentanglement and reconstruction on more-difficult data sets with unknown generative factors, where the flexibility of the WAE paradigm in the reconstruction term improves reconstructions.
Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
Probabilistic models with hierarchical-latent-variable structures provide state-of-the-art results amongst non-autoregressive, unsupervised density-based models.
Bayesian Online Meta-Learning
This work introduces a Bayesian online meta-learning framework to tackle the catastrophic forgetting and the sequential few-shot tasks problems.
Addressing Catastrophic Forgetting in Few-Shot Problems
We demonstrate that the popular gradient-based model-agnostic meta-learning algorithm (MAML) indeed suffers from catastrophic forgetting and introduce a Bayesian online meta-learning framework that tackles this problem.
Private Machine Learning via Randomised Response
We introduce a general learning framework for private machine learning based on randomised response.
HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models
We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with no changes to the model.
Variational f-divergence Minimization
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution.
Auxiliary Variational MCMC
We introduce Auxiliary Variational MCMC, a novel framework for learning MCMC kernels that combines recent advances in variational inference with insights drawn from traditional auxiliary variable MCMC methods such as Hamiltonian Monte Carlo.
Gaussian Mean Field Regularizes by Limiting Learned Information
Variational inference with a factorized Gaussian posterior estimate is a widely used approach for learning parameters and hidden variables.
Practical Lossless Compression with Latent Variables using Bits Back Coding
Deep latent variable models have seen recent success in many data domains.
Spread Divergence
For distributions $\mathbb{P}$ and $\mathbb{Q}$ with different supports or undefined densities, the divergence $\textrm{D}(\mathbb{P}||\mathbb{Q})$ may not exist.
Modular Networks: Learning to Decompose Neural Computation
Scaling model capacity has been vital in the success of deep learning.
Noisy Information Bottlenecks for Generalization
We propose Noisy Information Bottlenecks (NIB) to limit mutual information between learned parameters and the data through noise.
Training generative latent models by variational f-divergence minimization
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific form of f-divergence between the model and data distribution.
Stochastic Variational Optimization
These approaches are of particular interest because they are parallelizable.
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.
Generative Neural Machine Translation
We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences.
Generating Sentences Using a Dynamic Canvas
We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language.
Gaussian mixture models with Wasserstein distance
Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets.
Improving latent variable descriptiveness with AutoGen
Powerful generative models, particularly in Natural Language Modelling, are commonly trained by maximizing a variational lower bound on the data log likelihood.
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
In order to make our method scalable, we leverage recent block-diagonal Kronecker factored approximations to the curvature.
A Scalable Laplace Approximation for Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace and more
Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning
The capacity of an LSTM network can be increased by widening and adding layers.
Practical Gauss-Newton Optimisation for Deep Learning
We present an efficient block-diagonal ap- proximation to the Gauss-Newton matrix for feedforward neural networks.
Thinking Fast and Slow with Deep Learning and Tree Search
Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans.
Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent
We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods.
Dealing with a large number of classes -- Likelihood, Discrimination or Ranking?
We consider training probabilistic classifiers in the case of a large number of classes.
On solving Ordinary Differential Equations using Gaussian Processes
We describe a set of Gaussian Process based approaches that can be used to solve non-linear Ordinary Differential Equations.
A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes
This analysis leads naturally to the consideration of this approximate Newton method as an alternative gradient-based method for Markov Decision Processes.
Affine Independent Variational Inference
We present a method for approximate inference for a broad class of non-conjugate probabilistic models.
