A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New approach combines invariance and information bottleneck for OOD generalization.
Method learns representations invariant to task-irrelevant details in reinforcement learning tasks.
STAR improves equivariant and invariant representation learning by routing projection heads.
Performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Many image classification tasks, such as those related to cellular imaging, exhibit invariance to rotation. We present a novel scheme using the magnitude response of the 2D-discrete-Fourier transform (2D-DFT)…
New method learns time-invariant rewards from demonstrations.
Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing overfitting. We present a novel unsupervised invariance induction f…
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We decompose these errors into two complementary sources: sensitivity and invariance. We sh…
Improves contrastive learning invariance with novel training objectives and feature averaging.
Anti-transfer learning prevents misleading representations for speech tasks.
We focus on two supervised visual reasoning tasks whose labels encode a semantic relational rule between two or more objects in an image: the MNIST Parity task and the colorized Pentomino task. The objects in the images undergo random translation, scaling, rotation and coloring transformations. Thus these tasks involve…
Dida learns meta-features invariant to feature permutations.
Deep networks learn hierarchical data by invariant representations.
Word embeddings are commonly obtained as optimizers of a criterion function of a text corpus, but assessed on word-task performance using a different evaluation function of the test data. We contend that a possible source of disparity in performance on tasks is the incompatibility between classes of transformat…
Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance …
PeL separates sensory interface optimization from decision learning.
Novel framework improves graph learning for out-of-distribution generalization.
MetaPhysiCa tackles robust physics-informed machine learning for OOD tasks.
The paper explores how equivariant models' biases affect latent representations for better performance.
Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tas…
Recently, researchers have started applying convolutional neural networks (CNNs) with one-dimensional convolutions to clinical tasks involving time-series data. This is due, in part, to their computational efficiency, relative to recurrent neural networks and their ability to efficiently exploit certain temporal invari…
CNNs require fewer samples than LCNs and FCNs for image-based tasks due to locality and weight sharing.
Paper presents a world model that learns invariant causal features using contrastive unsupervised learning.
We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions. Invar…
SAM improves deep learning tasks by promoting balancedness, reducing outlier impact.
We add prior knowledge to deep networks to make them invariant to transformations.
ReCoRe learns invariant features for world navigation using contrastive learning and regularizers.
This work characterizes reward function partial identifiability and its impact on policy optimization.
Deep networks have achieved excellent results in perceptual tasks, yet their ability to generalize to variations not seen during training has come under increasing scrutiny. In this work we focus on their ability to have invariance towards the presence or absence of details. For example, humans are able to watch cartoo…
A framework isolates and learns approximately shared features for better domain adaptation.
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal is speaker prediction; we expect a performance improvement with this joint traini…
New method uses cycle consistency to enforce invariance in latent space.
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn in…
A new IL framework estimates invariant predictors with single domain data.
We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. Unlike popular approaches for encoding and decoding a set, our work does not rely on a carefully engineered network topology nor by any addit…
Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true for a subset of predictor variables: the conditional distribution of the target…
New method disentangles style features from data augmentations.
New MCMC method improves sampling efficiency across diverse structural models.
Proposes a method to predict responses from covariates over time.
Generative adversarial networks (GANs) are a powerful framework for generative tasks. However, they are difficult to train and tend to miss modes of the true data generation process. Although GANs can learn a rich representation of the covered modes of the data in their latent space, the framework misses an inverse map…
An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks …
SenSeI ensures fair models by enforcing invariance on sensitive groups.
HistNetQ improves quantification tasks by optimizing loss functions and eliminating label requirements.
Bayesian quadrature improves integration efficiency with invariant priors.
Counterfactual data augmentations may not ensure OOD robustness if performed by a context-guessing machine.
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances ar…
New algorithm learns invariant representations for robust neural networks.
Joint scene understanding and segmentation for automotive applications is a challenging problem in two key aspects:- (1) classifying every pixel in the entire scene and (2) performing this task under unstable weather and illumination changes (e.g. foggy weather), which results in poor outdoor scene visibility. This poo…