Zobrazeno 1 - 10
of 101
pro vyhledávání: '"Khan, Mohammad Emtiyaz"'
Publikováno v:
International Conference of Learning Representations 2024
Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed. Some of the issues can be addressed by estimating a distribution over the output, but in reality, such app
Externí odkaz:
http://arxiv.org/abs/2404.08168
Autor:
Shen, Yuesong, Daheim, Nico, Cong, Bai, Nickl, Peter, Marconi, Gian Maria, Bazan, Clement, Yokota, Rio, Gurevych, Iryna, Cremers, Daniel, Khan, Mohammad Emtiyaz, Möllenhoff, Thomas
We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for
Externí odkaz:
http://arxiv.org/abs/2402.17641
Autor:
Papamarkou, Theodore, Skoularidou, Maria, Palla, Konstantina, Aitchison, Laurence, Arbel, Julyan, Dunson, David, Filippone, Maurizio, Fortuin, Vincent, Hennig, Philipp, Hernández-Lobato, José Miguel, Hubin, Aliaksandr, Immer, Alexander, Karaletsos, Theofanis, Khan, Mohammad Emtiyaz, Kristiadi, Agustinus, Li, Yingzhen, Mandt, Stephan, Nemeth, Christopher, Osborne, Michael A., Rudner, Tim G. J., Rügamer, David, Teh, Yee Whye, Welling, Max, Wilson, Andrew Gordon, Zhang, Ruqi
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooke
Externí odkaz:
http://arxiv.org/abs/2402.00809
Understanding model's sensitivity to its training data is crucial but can also be challenging and costly, especially during training. To simplify such issues, we present the Memory-Perturbation Equation (MPE) which relates model's sensitivity to pert
Externí odkaz:
http://arxiv.org/abs/2310.19273
Autor:
Daheim, Nico, Möllenhoff, Thomas, Ponti, Edoardo Maria, Gurevych, Iryna, Khan, Mohammad Emtiyaz
Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a new uncertai
Externí odkaz:
http://arxiv.org/abs/2310.12808
Neural Processes (NPs) are appealing due to their ability to perform fast adaptation based on a context set. This set is encoded by a latent variable, which is often assumed to follow a simple distribution. However, in real-word settings, the context
Externí odkaz:
http://arxiv.org/abs/2306.15169
Sequential learning with Gaussian processes (GPs) is challenging when access to past data is limited, for example, in continual and active learning. In such cases, errors can accumulate over time due to inaccuracies in the posterior, hyperparameters,
Externí odkaz:
http://arxiv.org/abs/2306.03566
Autor:
Khan, Mohammad Emtiyaz
Publikováno v:
Presented at the 5th Symposium on Advances in Approximate Bayesian Inference (AABI 2023)
Variational Bayes is a popular method for approximate inference but its derivation can be cumbersome. To simplify the process, we give a 3-step recipe to identify the posterior form by explicitly looking for linearity with respect to expectations of
Externí odkaz:
http://arxiv.org/abs/2304.14251
The Bayesian Learning Rule provides a framework for generic algorithm design but can be difficult to use for three reasons. First, it requires a specific parameterization of exponential family. Second, it uses gradients which can be difficult to comp
Externí odkaz:
http://arxiv.org/abs/2303.04397
Autor:
Lin, Wu, Duruisseaux, Valentin, Leok, Melvin, Nielsen, Frank, Khan, Mohammad Emtiyaz, Schmidt, Mark
Riemannian submanifold optimization with momentum is computationally challenging because, to ensure that the iterates remain on the submanifold, we often need to solve difficult differential equations. Here, we simplify such difficulties for a class
Externí odkaz:
http://arxiv.org/abs/2302.09738