Search Results for author:
Found 15 papers, 15 papers with code
On the Importance of Embedding Norms in Self-Supervised Learning
While this seemingly implies that embedding norms cannot play any role in SSL, a few recent works have suggested that embedding norms have properties related to network convergence and confidence.
Delving into ChatGPT usage in academic writing through excess vocabulary
Large language models (LLMs) like ChatGPT can generate and revise text with human-level performance.
Learning representations of learning representations
The ICLR conference is unique among the top machine learning conferences in that all submitted papers are openly available.
Self-supervised Visualisation of Medical Image Datasets
Self-supervised learning methods based on data augmentations, such as SimCLR, BYOL, or DINO, allow obtaining semantically meaningful representations of image datasets and are widely used prior to supervised fine-tuning.
Persistent Homology for High-dimensional Data Based on Spectral Methods
As a remedy, we find that spectral distances on the k-nearest-neighbor graph of the data, such as diffusion distance and effective resistance, allow to detect the correct topology even in the presence of high-dimensional noise.
Unsupervised visualization of image datasets using contrastive learning
This problem can be circumvented by self-supervised approaches based on contrastive learning, such as SimCLR, relying on data augmentation to generate implicit neighbors, but these methods do not produce two-dimensional embeddings suitable for visualization.
From $t$-SNE to UMAP with contrastive learning
We exploit this new conceptual connection to propose and implement a generalization of negative sampling, allowing us to interpolate between (and even extrapolate beyond) $t$-SNE and UMAP and their respective embeddings.
Wasserstein t-SNE
We use t-SNE to construct 2D embeddings of the units, based on the matrix of pairwise Wasserstein distances between them.
Tracking excess mortality across countries during the COVID-19 pandemic with the World Mortality Dataset
Comparing the impact of the COVID-19 pandemic between countries or across time is difficult because the reported numbers of cases and deaths can be strongly affected by testing capacity and reporting policy.
Scaling Down Deep Learning with MNIST-1D
Although deep learning models have taken on commercial and political relevance, key aspects of their training and operation remain poorly understood.
Attraction-Repulsion Spectrum in Neighbor Embeddings
Neighbor embeddings are a family of methods for visualizing complex high-dimensional datasets using $k$NN graphs.
Sparse bottleneck neural networks for exploratory non-linear visualization of Patch-seq data
Patch-seq, a recently developed experimental technique, allows neuroscientists to obtain transcriptomic and electrophysiological information from the same neurons.
Heavy-tailed kernels reveal a finer cluster structure in t-SNE visualisations
T-distributed stochastic neighbour embedding (t-SNE) is a widely used data visualisation technique.
Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization
We use a spiked covariance model as an analytically tractable example and prove that the optimal ridge penalty in this case is negative when $n\ll p$.
Demixed principal component analysis of population activity in higher cortical areas reveals independent representation of task parameters
Neurons in higher cortical areas, such as the prefrontal cortex, are known to be tuned to a variety of sensory and motor variables.
