Search Results for author:
Found 18 papers, 7 papers with code
PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
With those metrics we identify tasks which are challenging for recent ML methods and propose these tasks as future challenges for the community.
Learning Neural PDE Solvers with Parameter-Guided Channel Attention
The experiments also show several advantages of CAPE, such as its increased ability to generalize to unseen PDE parameters without large increases inference time and parameter count.
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
Long-range interactions are essential for the correct description of complex systems in many scientific fields.
Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
We propose a simple yet powerful test statistic to quantify the discrepancy between two conditional distributions.
Measuring Dependence with Matrix-based Entropy Functional
Measuring the dependence of data plays a central role in statistics and machine learning.
Principle of Relevant Information for Graph Sparsification
Graph sparsification aims to reduce the number of edges of a graph while maintaining its structural properties.
Gated Information Bottleneck for Generalization in Sequential Environments
By learning minimum sufficient representations from training data, the information bottleneck (IB) approach has demonstrated its effectiveness to improve generalization in different AI applications.
Adversarial Robustness
Out of Distribution (OOD) Detection
+1
Efficient and Scalable Multi-task Regression on Massive Number of Tasks
Scaling up MTL methods to problems with a tremendous number of tasks is a big challenge.
Towards Interpretable Multi-Task Learning Using Bilevel Programming
Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models.
Learning an Interpretable Graph Structure in Multi-Task Learning
We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph.
Bilevel Continual Learning
This paper presents Bilevel Continual Learning (BiCL), a general framework for continual learning that fuses bilevel optimization and recent advances in meta-learning for deep neural networks.
Modular-Relatedness for Continual Learning
In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting.
BiGrad: Differentiating through Bilevel Optimization Programming
We describe a class of gradient estimators for the combinatorial case which reduces the requirements in term of computation complexity; for the continuous variables case the gradient computation takes advantage of push-back approach (i. e. vector-jacobian product) for an efficient implementation.
Human-Centric Research for NLP: Towards a Definition and Guiding Questions
With Human-Centric Research (HCR) we can steer research activities so that the research outcome is beneficial for human stakeholders, such as end users.
Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming
Integrating bilevel mathematical programming within deep learning is thus an essential objective for the Machine Learning community.
Self-Tuning Hamiltonian Monte Carlo for Accelerated Sampling
In the case of alanine dipeptide, by tuning the only free parameter of our loss definition, we find a good correspondence between it and the autocorrelation times, resulting in a $>100$ fold speed up in optimization of simulation parameters compared to a grid-search.
Continual Invariant Risk Minimization
Invariant risk minimization (IRM) is a recent proposal for discovering environment-invariant representations.
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
Existing biased and unbiased MD simulations, however, are prone to miss either rare events or extrapolative regions -- areas of the configurational space where unreliable predictions are made.
