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.
RID framework quantifies and regularizes task-relevant knowledge in distillation.
InfoPrompt improves soft prompt tuning by maximizing mutual information, leading to better performance.
Estimates latent dimensionality for prediction tasks using mutual information.
New meta-RL method avoids exploration-exploitation trade-off.
GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.
Extends V-IP framework to use LLMs for generating task-relevant concepts, improving interpretability and performance.
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to poor task performanc…
Study identifies specialist representations from generalist models without parametric constraints.
Paper analyzes dataset distillation for efficient encoding of task-relevant information.
Paper proposes a method to make learned models focus on task-relevant information.
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing domains, possibly by leveraging complex molecular machinery to solve many t…
Robotics improves by using image search to solve new tasks.
fMRI is a unique non-invasive approach for understanding the functional organization of the human brain, and task-based fMRI promotes identification of functionally relevant brain regions associated with a given task. Here, we use fMRI (using the Poffenberger Paradigm) data collected in mono- and dizygotic twin pairs t…
Information mapping is a popular application of Multivoxel Pattern Analysis (MVPA) to fMRI. Information maps are constructed using the so called searchlight method, where the spherical multivoxel neighborhood of every voxel (i.e., a searchlight) in the brain is evaluated for the presence of task-relevant response patte…
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in the agent, forcing it to focus on task-relevant information by sequentially que…
Study how models represent features in naturalistic learning problems.
A measure of neural complexity quantifies how hard it is to access information across neurons.
Top-down attention allows people to focus on task-relevant visual information. Is the resulting perceptual boost task-dependent in naturalistic settings? We aim to answer this with a large-scale computational experiment. First, we design a collection of visual tasks, each consisting of classifying images from a chosen …
HCL learns shared and modality-specific latent representations for multimodal data.
Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and often contains information irrelevant to the assistant. This makes it harder for …
Study quantifies interactions between unlabeled multimodal data.
This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's …
This paper analyzes self-supervised learning from a multi-view perspective.
We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is achieved by explicitly separating the state-action spaces across the hierarchy, which…
New method learns graph structure and uncertainty from data.
Method learns representations invariant to task-irrelevant details in reinforcement learning tasks.
While deep representation learning has become increasingly capable of separating task-relevant representations from other confounding factors in the data, two significant challenges remain. First, there is often an unknown and potentially infinite number of confounding factors coinciding in the data. Second, not all of…
Unified framework for hybrid learning and optimization via active inference.
Proposes a framework for extracting consistent physiological features across users.
Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data constrains samples to a manifold of dramatically lower dimensionality. Learning to identify and extract task-relevant variables from this embedde…
HydaLearn dynamically adjusts task weights for better MTL performance.
In this paper we explore the richness of information captured by the latent space of a vision-based generative model. The model combines unsupervised generative learning with a task-based performance predictor to learn and to exploit task-relevant object affordances given visual observations from a reaching task, invol…
This paper proposes an alternative to E2E training for deep networks, reducing memory footprint.
Robotic grasp stability improved with fingertip slippage detection.
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…
Animals need to devise strategies to maximize returns while interacting with their environment based on incoming noisy sensory observations. Task-relevant states, such as the agent's location within an environment or the presence of a predator, are often not directly observable but must be inferred using available sens…
Supervised topic models are often sought to balance prediction quality and interpretability. However, when models are (inevitably) misspecified, standard approaches rarely deliver on both. We introduce a novel approach, the prediction-focused topic model, that uses the supervisory signal to retain only vocabulary terms…
Complex statistical machine learning models are increasingly being used or considered for use in high-stakes decision-making pipelines in domains such as financial services, health care, criminal justice and human services. These models are often investigated as possible improvements over more classical tools such as r…
We propose a method for finding alternate features missing in the Lasso optimal solution. In ordinary Lasso problem, one global optimum is obtained and the resulting features are interpreted as task-relevant features. However, this can overlook possibly relevant features not selected by the Lasso. With the proposed met…
RényiCL uses Rényi divergence for robust contrastive learning with stronger data augmentations.
New framework aligns latent representations over-the-air using intelligent metasurfaces.
Regularization effect found in neural feature alignment.
Deep learning extracts terrain texture covariates for geostatistical modeling.
Analysis of pretrained models' effectiveness in downstream tasks.
Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.
Stock market volatility forecasting is a task relevant to assessing market risk. We investigate the interaction between news and prices for the one-day-ahead volatility prediction using state-of-the-art deep learning approaches. The proposed models are trained either end-to-end or using sentence encoders transfered fro…
The study reveals how attention paths in Transformers influence learning outcomes.
Improved fMRI analysis models enhance classification performance and select relevant brain regions.