no code implementations • 19 Feb 2024 • Mingtian Zhang, Shawn Lan, Peter Hayes, David Barber
Our results demonstrate that Mafin significantly enhances the performance of the black-box embeddings by only requiring the training of a small augmented model.
no code implementations • 12 Feb 2024 • William Muldrew, Peter Hayes, Mingtian Zhang, David Barber
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.
1 code implementation • 5 Feb 2024 • Wenlin Chen, Mingtian Zhang, Brooks Paige, José Miguel Hernández-Lobato, David Barber
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.
1 code implementation • 29 Aug 2023 • Liyuan Wang, Xingxing Zhang, Qian Li, Mingtian Zhang, Hang Su, Jun Zhu, Yi Zhong
Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world.
no code implementations • 1 Jun 2023 • Andi Zhang, Mingtian Zhang, Damon Wischik
We propose a probabilistic perspective on adversarial examples.
1 code implementation • NeurIPS 2023 • Mingtian Zhang, Alex Hawkins-Hooker, Brooks Paige, David Barber
Energy-Based Models (EBMs) offer a versatile framework for modeling complex data distributions.
no code implementations • 15 Sep 2022 • Mingtian Zhang, Oscar Key, Peter Hayes, David Barber, Brooks Paige, François-Xavier Briol
Score-based divergences have been widely used in machine learning and statistics applications.
no code implementations • 19 Jun 2022 • Peter Hayes, Mingtian Zhang, Raza Habib, Jordan Burgess, Emine Yilmaz, David Barber
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.
no code implementations • 8 Jun 2022 • Mingtian Zhang, Andi Zhang, Tim Z. Xiao, Yitong Sun, Steven McDonagh
In this work, we propose to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 28 May 2022 • Mingtian Zhang, Tim Z. Xiao, Brooks Paige, David Barber
Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images.
1 code implementation • 23 May 2022 • Mingtian Zhang, Peter Hayes, David Barber
The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression.
2 code implementations • 13 Jan 2022 • Mingtian Zhang, James Townsend, Ning Kang, David Barber
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.
1 code implementation • NeurIPS 2021 • Liyuan Wang, Mingtian Zhang, Zhongfan Jia, Qian Li, Chenglong Bao, Kaisheng Ma, Jun Zhu, Yi Zhong
Without accessing to the old training samples, knowledge transfer from the old tasks to each new task is difficult to determine, which might be either positive or negative.
no code implementations • 29 Sep 2021 • Diego Granziol, Mingtian Zhang, Nicholas Baskerville
Under a PAC-Bayesian framework, we derive an implementation efficient parameterisation invariant metric to measure the difference between our true and empirical risk.
no code implementations • 29 Sep 2021 • Mingtian Zhang, Yitong Sun, Chen Zhang, Steven McDonagh
Flow-based models typically define a latent space with dimensionality identical to the observational space.
2 code implementations • NeurIPS 2021 • Mingtian Zhang, Andi Zhang, Steven McDonagh
Out-of-distribution (OOD) detection and lossless compression constitute two problems that can be solved by the training of probabilistic models on a first dataset with subsequent likelihood evaluation on a second dataset, where data distributions differ.
Out-of-Distribution Generalization Out of Distribution (OOD) Detection
no code implementations • ICLR Workshop SSL-RL 2021 • Mingtian Zhang, Peter Noel Hayes, Tim Z. Xiao, Andi Zhang, David Barber
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 +1
no code implementations • 1 Jan 2021 • Mingtian Zhang, Yitong Sun, Steven McDonagh, Chen Zhang
Flow-based generative models typically define a latent space with dimensionality identical to the observational space.
no code implementations • 1 Jan 2021 • Chen Zhang, Yitong Sun, Mingtian Zhang
However, in this paper, we point out that the method taken by GIN for informative latent variables identification is not theoretically supported and can be disproved by experiments.
no code implementations • 30 Jul 2019 • Mohammed Amin Abdullah, Hang Ren, Haitham Bou Ammar, Vladimir Milenkovic, Rui Luo, Mingtian Zhang, Jun Wang
Reinforcement learning algorithms, though successful, tend to over-fit to training environments hampering their application to the real-world.
no code implementations • 27 Jul 2019 • Mingtian Zhang, Thomas Bird, Raza Habib, Tianlin Xu, David Barber
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution.
no code implementations • 21 Nov 2018 • Mingtian Zhang, Peter Hayes, Tom Bird, Raza Habib, David Barber
For distributions $\mathbb{P}$ and $\mathbb{Q}$ with different supports or undefined densities, the divergence $\textrm{D}(\mathbb{P}||\mathbb{Q})$ may not exist.
no code implementations • 27 Sep 2018 • Mingtian Zhang, Thomas Bird, Raza Habib, Tianlin Xu, David Barber
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific form of f-divergence between the model and data distribution.