Search Results for author:
Found 6 papers, 2 papers with code
Fusion of Graph Neural Networks via Optimal Transport
Finally, we present results suggesting that model fusion using OT is harder in the case of GCNs than MLPs and that incorporating the graph structure into the process does not improve the performance of the method.
Position: Curvature Matrices Should Be Democratized via Linear Operators
Structured large matrices are prevalent in machine learning.
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs).
Standardizing Structural Causal Models
Moreover, contrary to the post-hoc standardization of data generated by standard SCMs, we prove that linear iSCMs are less identifiable from prior knowledge on the weights and do not collapse to deterministic relationships in large systems, which may make iSCMs a useful model in causal inference beyond the benchmarking problem studied here.
Transition Constrained Bayesian Optimization via Markov Decision Processes
This is a parallel to the optimization of an acquisition function in policy space.
Estimating value at risk: LSTM vs. GARCH
Estimating value-at-risk on time series data with possibly heteroscedastic dynamics is a highly challenging task.
