Search Results for author:
Found 19 papers, 14 papers with code
Effectively Modeling Time Series with Simple Discrete State Spaces
For expressivity, we propose a new SSM parameterization based on the companion matrix -- a canonical representation for discrete-time processes -- which enables SpaceTime's SSM layers to learn desirable autoregressive processes.
S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces
On ImageNet-1k, S4ND exceeds the performance of a Vision Transformer baseline by $1. 5\%$ when training with a $1$D sequence of patches, and matches ConvNeXt when modeling images in $2$D.
On the Parameterization and Initialization of Diagonal State Space Models
On the other hand, a recent variant of S4 called DSS showed that restricting the state matrix to be fully diagonal can still preserve the performance of the original model when using a specific initialization based on approximating S4's matrix.
It's Raw! Audio Generation with State-Space Models
SaShiMi yields state-of-the-art performance for unconditional waveform generation in the autoregressive setting.
Personalized Benchmarking with the Ludwig Benchmarking Toolkit
LBT provides a configurable interface for controlling training and customizing evaluation, a standardized training framework for eliminating confounding variables, and support for multi-objective evaluation.
Efficiently Modeling Long Sequences with Structured State Spaces
A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies.
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations (NDEs) are popular families of deep learning models for time-series data, each with unique strengths and tradeoffs in modeling power and computational efficiency.
Ranked #2 on
Sequential Image Classification
on Sequential MNIST
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Managing ML Pipelines: Feature Stores and the Coming Wave of Embedding Ecosystems
The industrial machine learning pipeline requires iterating on model features, training and deploying models, and monitoring deployed models at scale.
Mandoline: Model Evaluation under Distribution Shift
If an unlabeled sample from the target distribution is available, along with a labeled sample from a possibly different source distribution, standard approaches such as importance weighting can be applied to estimate performance on the target.
Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems
If not, how easily can such a system be repurposed for their use case?
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers
Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations (NDEs) are popular families of deep learning models for time-series data, each with unique strengths and tradeoffs in modeling power and computational efficiency.
SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive text summarization.
Robustness Gym: Unifying the NLP Evaluation Landscape
Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems.
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
Particularly concerning are models with inconsistent performance on specific subgroups of a class, e. g., exhibiting disparities in skin cancer classification in the presence or absence of a spurious bandage.
Learning Procedural Abstractions and Evaluating Discrete Latent Temporal Structure
Given a dataset of time-series, the goal is to identify the latent sequence of steps common to them and label each time-series with the temporal extent of these procedural steps.
PLOTS: Procedure Learning from Observations using Subtask Structure
In many cases an intelligent agent may want to learn how to mimic a single observed demonstrated trajectory.
Sample Efficient Policy Search for Optimal Stopping Domains
Optimal stopping problems consider the question of deciding when to stop an observation-generating process in order to maximize a return.
Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing
We present Octopus, an AI agent to jointly balance three conflicting task objectives on a micro-crowdsourcing marketplace - the quality of work, total cost incurred, and time to completion.
