skip to main content


Title: A Hypergradient Approach to Robust Regression without Correspondence
We consider a regression problem, where the correspondence between the input and output data is not available. Such shuffled data are commonly observed in many real world problems. Take flow cytometry as an example: the measuring instruments are unable to preserve the correspondence between the samples and the measurements. Due to the combinatorial nature of the problem, most of the existing methods are only applicable when the sample size is small, and are limited to linear regression models. To overcome such bottlenecks, we propose a new computational framework --- ROBOT --- for the shuffled regression problem, which is applicable to large data and complex models. Specifically, we propose to formulate regression without correspondence as a continuous optimization problem. Then by exploiting the interaction between the regression model and the data correspondence, we propose to develop a hypergradient approach based on differentiable programming techniques. Such a hypergradient approach essentially views the data correspondence as an operator of the regression model, and therefore it allows us to find a better descent direction for the model parameters by differentiating through the data correspondence. ROBOT is quite general, and can be further extended to an inexact correspondence setting, where the input and output data are not necessarily exactly aligned. Thorough numerical experiments show that ROBOT achieves better performance than existing methods in both linear and nonlinear regression tasks, including real-world applications such as flow cytometry and multi-object tracking.  more » « less
Award ID(s):
1925263
PAR ID:
10238815
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
International Conference on Learning Representations
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The main drawbacks of input-output linearizing controllers are the need for precise dynamics models and not being able to account for input constraints. Model uncertainty is common in almost every robotic application and input saturation is present in every real world system. In this paper, we address both challenges for the specific case of bipedal robot control by the use of reinforcement learning techniques. Taking the structure of a standard input-output linearizing controller, we use an additive learned term that compensates for model uncertainty. Moreover, by adding constraints to the learning problem we manage to boost the performance of the final controller when input limits are present. We demonstrate the effectiveness of the designed framework for different levels of uncertainty on the five-link planar walking robot RABBIT. 
    more » « less
  2. This is the first paper to approach the problem of bias in the output of a stochastic simulation due to us- ing input distributions whose parameters were estimated from real-world data. We consider, in particular, the bias in simulation-based estimators of the expected value (long-run average) of the real-world system performance; this bias will be present even if one employs unbiased estimators of the input distribution parameters due to the (typically) nonlinear relationship between these parameters and the output response. To date this bias has been assumed to be negligible because it decreases rapidly as the quantity of real-world input data increases. While true asymptotically, this property does not imply that the bias is actually small when, as is always the case, data are finite. We present a delta-method approach to bias estimation that evaluates the nonlinearity of the expected-value performance surface as a function of the input-model parameters. Since this response surface is unknown, we propose an innovative experimental design to fit a response-surface model that facilitates a test for detecting a bias of a relevant size with specified power. We evaluate the method using controlled experiments, and demonstrate it through a realistic case study concerning a healthcare call centre. 
    more » « less
  3. Abstract

    In linear regression, the coefficients are simple to estimate using the least squares method with a known design matrix for the observed measurements. However, real-world applications may encounter complications such as an unknown design matrix and complex-valued parameters. The design matrix can be estimated from prior information but can potentially cause an inverse problem when multiplying by the transpose as it is generally ill-conditioned. This can be combat by adding regularizers to the model but does not always mitigate the issues. Here, we propose our Bayesian approach to a complex-valued latent variable linear model with an application to functional magnetic resonance imaging (fMRI) image reconstruction. The complex-valued linear model and our Bayesian model are evaluated through extensive simulations and applied to experimental fMRI data.

     
    more » « less
  4. Aleksandra Faust, David Hsu (Ed.)
    Modern Reinforcement Learning (RL) algorithms are not sample efficient to train on multi-step tasks in complex domains, impeding their wider deployment in the real world. We address this problem by leveraging the insight that RL models trained to complete one set of tasks can be repurposed to complete related tasks when given just a handful of demonstrations. Based upon this insight, we propose See-SPOT-Run (SSR), a new computational approach to robot learning that enables a robot to complete a variety of real robot tasks in novel problem domains without task-specific training. SSR uses pretrained RL models to create vectors that represent model, task, and action relevance in demonstration and test scenes. SSR then compares these vectors via our Cycle Consistency Distance (CCD) metric to determine the next action to take. SSR completes 58% more task steps and 20% more trials than a baseline few-shot learning method that requires task-specific training. SSR also achieves a four order of magnitude improvement in compute efficiency and a 20% to three order of magnitude improvement in sample efficiency compared to the baseline and to training RL models from scratch. To our knowledge, we are the first to address multi-step tasks from demonstration on a real robot without task-specific training, where both the visual input and action space output are high dimensional. Code is available in the supplement. 
    more » « less
  5. Abstract

    We study the problem of fitting a piecewise affine (PWA) function to input–output data. Our algorithm divides the input domain into finitely many regions whose shapes are specified by a user-provided template and such that the input–output data in each region are fit by an affine function within a user-provided error tolerance. We first prove that this problem is NP-hard. Then, we present a top-down algorithmic approach for solving the problem. The algorithm considers subsets of the data points in a systematic manner, trying to fit an affine function for each subset using linear regression. If regression fails on a subset, the algorithm extracts a minimal set of points from the subset (an unsatisfiable core) that is responsible for the failure. The identified core is then used to split the current subset into smaller ones. By combining this top-down scheme with a set-covering algorithm, we derive an overall approach that provides optimal PWA models for a given error tolerance, where optimality refers to minimizing the number of pieces of the PWA model. We demonstrate our approach on three numerical examples that include PWA approximations of a widely used nonlinear insulin–glucose regulation model and a double inverted pendulum with soft contacts.

     
    more » « less