Zobrazeno 1 - 10
of 2 235
pro vyhledávání: '"Archambeau A"'
Autor:
Franceschi, Luca, Donini, Michele, Perrone, Valerio, Klein, Aaron, Archambeau, Cédric, Seeger, Matthias, Pontil, Massimiliano, Frasconi, Paolo
Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the choice of their values determine the effectiveness of systems based on th
Externí odkaz:
http://arxiv.org/abs/2410.22854
Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in real-worl
Externí odkaz:
http://arxiv.org/abs/2405.02267
A large branch of explainable machine learning is grounded in cooperative game theory. However, research indicates that game-theoretic explanations may mislead or be hard to interpret. We argue that often there is a critical mismatch between what one
Externí odkaz:
http://arxiv.org/abs/2402.09947
With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass to obtain
Externí odkaz:
http://arxiv.org/abs/2312.05021
Large language models (LLMs) encode vast amounts of world knowledge. However, since these models are trained on large swaths of internet data, they are at risk of inordinately capturing information about dominant groups. This imbalance can propagate
Externí odkaz:
http://arxiv.org/abs/2310.14777
Many state-of-the-art hyperparameter optimization (HPO) algorithms rely on model-based optimizers that learn surrogate models of the target function to guide the search. Gaussian processes are the de facto surrogate model due to their ability to capt
Externí odkaz:
http://arxiv.org/abs/2305.03623
Continual learning enables the incremental training of machine learning models on non-stationary data streams.While academic interest in the topic is high, there is little indication of the use of state-of-the-art continual learning algorithms in pra
Externí odkaz:
http://arxiv.org/abs/2304.12067
Autor:
Detommaso, Gianluca, Gasparin, Alberto, Donini, Michele, Seeger, Matthias, Wilson, Andrew Gordon, Archambeau, Cedric
We present Fortuna, an open-source library for uncertainty quantification in deep learning. Fortuna supports a range of calibration techniques, such as conformal prediction that can be applied to any trained neural network to generate reliable uncert
Externí odkaz:
http://arxiv.org/abs/2302.04019
Autor:
Vietri, Giuseppe, Archambeau, Cedric, Aydore, Sergul, Brown, William, Kearns, Michael, Roth, Aaron, Siva, Ankit, Tang, Shuai, Wu, Zhiwei Steven
We provide a differentially private algorithm for producing synthetic data simultaneously useful for multiple tasks: marginal queries and multitask machine learning (ML). A key innovation in our algorithm is the ability to directly handle numerical f
Externí odkaz:
http://arxiv.org/abs/2209.07400
As we move away from the data, the predictive uncertainty should increase, since a great variety of explanations are consistent with the little available information. We introduce Distance-Aware Prior (DAP) calibration, a method to correct overconfid
Externí odkaz:
http://arxiv.org/abs/2207.08200