Paper shows robust generative learning with minimal assumptions on target distributions.
problem Learning generative models with minimal assumptions on target distributions.
method Lipschitz-regularized α-divergences with minimal assumptions. result Stable learning across various target distributions with minimal assumptions.
A new method improves stability in policy learning for continuous control tasks.
problem Stability issues in policy gradient methods when policies are close to deterministic.
method Target Distribution Learning (TDL) alternates between proposing a target distribution and training the policy network to approach it.
result TDL leads to more stable policy improvements over iterations compared to existing methods.
SIXO improves inference by learning smoothing distributions from all observations.
problem Inference limitations due to ignoring future observations in filtering distributions.
method Density ratio estimation to warp filtering distributions into smoothing distributions, then use SMC with learned targets.
result Proves tighter log marginal lower bounds and more accurate inferences and estimates.
DRDA robustly adapts models across domains with mismatched distributions.
problem Vulnerability of DA methods to noise and inability to generalize to unseen samples.
method DRDA uses distributionally robust optimization (DRO) with MMD metric to learn robust decision functions.
result DRDA outperforms existing robust learning approaches in experiments.
Generative multitask learning mitigates confounders causing targets.
problem Unobserved confounders causing targets but not inputs.
method Generative multitask learning (GMTL) modifies inference objective to remove joint target influence.
result Improved robustness to target shift across multitask learning methods.
DM improves self-supervised transfer learning by matching target distributions.
problem Improving self-supervised transfer learning performance.
method Distribution Matching (DM) method that drives representation distribution towards a predefined reference distribution.
result DM outperforms existing methods on target classification tasks.
MT-SGD samples from multiple target distributions using gradient descent.
problem Sampling from multiple unnormalized target distributions.
method Proposes MT-SGD, a flow of intermediate distributions to sample from multiple target distributions.
result Asymptotic analysis shows MT-SGD reduces to multiple-gradient descent for multi-objective optimization.
Paper learns domain randomization distributions for robust robot policies.
problem Finding good domain randomization parameters for simulation without real data.
method Gradient-based search methods to learn domain randomization distribution.
result Improvements in jump-start and asymptotic performance when transferring policies.
ATC predicts target domain accuracy using only labeled and unlabeled data.
problem Predicting out-of-distribution performance with limited labeled data.
method Average Thresholded Confidence (ATC) method that learns a threshold on model confidence.
result ATC outperforms previous methods across various types of distribution shifts and datasets.
Paper proposes a shape-constrained approach to distributionally robust learning.
problem Challenges in statistical learning under distribution shift.
method Shape-constrained approach to distributionally robust learning (DRL). Assumes isotonic density ratio.
result Improved accuracy demonstrated in empirical studies.
Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access to: (1) easily obtained labelled data from a related source domain, which may ha…
In this paper, a new approach for classification of target task using limited labeled target data as well as enormous unlabeled source data is proposed which is called self-taught learning. The target and source data can be drawn from different distributions. In the previous approaches, covariate shift assumption is co…
Estimates model performance under distribution shift using domain-invariant predictors.
problem Poor performance of models on test distributions different from training distributions.
method Uses domain-invariant predictors as a proxy for unknown target labels.
result Shows that the complexity of latent representations influences target risk.
This research improves online learning by correcting for target shift in machine learning.
problem Online learning struggles with distributional shift, especially in target values.
method Derives closed-form expressions for online and offline learning, and target correction.
result Online kernel-based learning can learn the same predictor as offline learning with target correction.
Proposes PGPS for efficient Bayesian inference.
problem Efficient sampling from complex posterior distributions.
method Path-guided particle-based sampling with Log-weighted Shrinkage.
result PGPS generates samples closer to target distribution.
A new method called TemperFlow tackles multimodality in sampling from unnormalized distributions.
problem Sampling from unnormalized distributions with isolated modes.
method TemperFlow learns a sequence of tempered distributions to progressively approach the target distribution.
result TemperFlow overcomes the limitations of existing methods and achieves superior performance.
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…
Improves domain adaptation by combining multiple source domains and target domain data.
problem Poor performance of empirical risk minimization in distributionally shifted target domains.
method Distributionally robust model optimizing adversarial reward based on explained variance across multiple source domains.
result The robust model is a weighted average of conditional outcome models from source domains.
LDAO addresses imbalanced regression by learning local distribution structures.
problem Imbalanced regression with sparse target regions difficult for models.
method LDAO learns local distribution structures, models and samples from each, then merges.
result LDAO outperforms state-of-the-art methods on 45 imbalanced datasets.
Paper tackles continuous transfer learning with evolving target domains.
problem Challenges of negative transfer in evolving target domains.
method Proposes label-informed C-divergence for measuring distribution shift and negative transfer.
result Demonstrates effectiveness of TransLATE framework in minimizing classification error and C-divergence.
Reweighting training data to better represent new tasks.
problem Deploying machine learning models to new tasks is challenging due to training data distribution.
method Formulate an exponential tilt distribution shift model and learn train data importance weights to minimize KL divergence.
result The learned train data weights improve target performance evaluation, fine-tuning, and model selection.
Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focused on exploring invariant representations that have similar distributions across domains. However, w…
Algorithm adapts pretrained semantic segmentation models to new domains.
problem Adapting pretrained models to new, unlabeled domains without source data.
method Learn prototypical distribution in embedding space, align target domain with source domain.
result Method achieves competitive performance on benchmark tasks.
New perspective on distribution shift helps make learning easier.
problem Learning with different training and target distributions.
method Formalizing and exploring Positive Distribution Shift (PDS).
result Distribution shift can be positive, making learning easier.
EnMDAP aligns conditional distributions for multi-source domain adaptation using pseudolabels.
problem Training a target model with no labeled data in the absence of target data labels.
method EnMDAP uses label-wise moment matching and ensemble learning with multiple feature extractors.
result EnMDAP achieves state-of-the-art performance in multi-source domain adaptation tasks.
A novel framework synthesizes treatment data across sites using optimal transport.
problem Estimating treatment effects across different sites with varying conditions.
method Distributional causal inference, Optimal Transport for alignment of control group distributions.
result Synthetic treatment group data aligns with true target distribution under general conditions.
SPOT uses optimal transport to select important prototypes.
problem Summarizing datasets for better understanding and decision making.
method Modeling prototype selection as a submodular optimization problem and using a greedy algorithm.
result Our approach efficiently selects prototypes with optimal transport that best represent the target dataset.
Early stopping in meta-learning improved by analyzing neural activation patterns.
problem Early stopping in few-shot learning is challenging due to distributional shifts between meta-validation and meta-test sets.
method Activation-Based Early-stopping (ABE) analyzes hidden layer activations from unlabelled support examples to detect when target generalization diverges from source data.
result Simple activation statistics can effectively estimate target generalization, improving few-shot transfer learning across various algorithms and datasets.
The paper studies how different entropic regularizations affect GAN solutions.
problem Improving numerical convergence and sparsity in GAN solutions.
method Entropic regularization of Wasserstein distance and Sinkhorn divergence.
result Entropy regularization promotes sparsity, while Sinkhorn divergence recovers unregularized solution.
Develops estimators for near-optimal linear regression under distribution shift.
problem Linear regression under distribution shift with scarce target domain data.
method Minimax linear risk estimators covering various transfer learning settings.
result Achieves near-optimal risk for linear regression problems under distribution shift.
Enhanced Bayesian target encoding uses sampling techniques to improve model performance.
problem Improving target encoding for better model performance in machine learning.
method Using sampling techniques in Bayesian target encoding to extract intra-category distribution information.
result Improves generalization and reduces target leakage in machine learning models.
This paper analyzes the difficulty of unsupervised domain adaptation using information theory.
problem The challenge of unsupervised domain adaptation under covariate shift.
method Formulates the problem using a distribution π in the ground-truth triples (p, q, f), defines optimal learner performance, and introduces PTLU for quantifying difficulty.
result Characterizes the optimal learner and introduces PTLU as a measure of UDA difficulty.
Under covariate shift, training (source) data and testing (target) data differ in input space distribution, but share the same conditional label distribution. This poses a challenging machine learning task. Robust Bias-Aware (RBA) prediction provides the conditional label distribution that is robust to the worstcase lo…
We consider the problem of search through comparisons, where a user is presented with two candidate objects and reveals which is closer to her intended target. We study adaptive strategies for finding the target, that require knowledge of rank relationships but not actual distances between objects. We propose a new str…
Deep model tackles zero-inflated multi-species abundance estimation.
problem Predicting species distribution across landscapes with inflated zero counts.
method Proposes a novel deep learning model combining multivariate probit and log-normal distributions.
result Model outperforms existing methods on bird and fish population datasets.
This paper introduces a neural sampler for scalable sampling from complex distributions.
problem Efficiently sampling from high-dimensional un-normalized distributions.
method Neural implicit sampler trained with KL and Fisher divergence methods.
result The neural sampler generates large batches of samples with low computational costs.
New approach tackles domain adaptation without assuming domain invariant representations.
problem Learning models on source domains for target domains with labeled and unlabeled data.
method Hidden Covariate Shift hypothesis; learning representation to match joint distributions.
result State-of-the-art performance on Amazon Reviews dataset.
CUDA CTDR tackles unsupervised domain adaptation without domain alignment.
problem Lack of direct methods for unlabeled target domain classification.
method Jointly learns CTDR on source and target distributions using contradistinguish loss and supervised loss.
result CUDA CTDR achieves state-of-the-art results on various domain adaptation datasets.
Robotic grasping system learns to target objects from a single image.
problem Robotic grasping in unstructured environments.
method Distributed reinforcement learning, active vision, synchronous SGD.
result System learns to grasp unseen objects without retraining.
Improves sample efficiency in reinforcement learning by controlling task distribution.
problem Learning and generalization of behaviors across related tasks in intelligent robots.
method Introduces a novel relative entropy reinforcement learning algorithm that allows the agent to control the intermediate task distribution.
result The proposed curriculum learning scheme drastically improves sample efficiency and enables learning in challenging scenarios.
Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different. Current theoretical results show that the efficiency of DA algorithms depends on their capacity of …
Efficient algorithm for learning halfspaces in a new model with polynomial time complexity.
problem Learning halfspaces in the testable learning model with distributional constraints.
method Developed new tests using labels and combined with moment-matching approach.
result Achieved near optimal error rates for Gaussian and strongly log-concave distributions.
Emputation learns imputation models guided by missingness assumptions.
problem Learning imputation models for missing data given observed data.
method Guided by specific missingness assumptions, Emputation trains a deep generative model to learn the extrapolation distribution of missing variables.
result The population minimizer of the emputation risk recovers the target extrapolation distribution under various identification assumptions.
Paper proposes a novel online transfer learning method to reduce domain discrepancy.
problem Online transfer learning with online distribution discrepancy minimization.
method The method seeks a new feature representation to simultaneously reduce marginal and conditional distribution discrepancies.
result The proposed method outperforms state-of-the-art methods in comprehensive experiments.
Proposes a deep model for Bayesian quantile regression without Gaussian assumptions.
problem Uncertainty quantification from single forward-pass models is computationally expensive and restrictive.
method Deep evidential learning for Bayesian quantile regression.
result Achieves calibrated uncertainties on non-Gaussian distributions.
Data-target pairing is an important step towards multi-target localization for the intelligent operation of unmanned systems. Target localization plays a crucial role in numerous applications, such as search, and rescue missions, traffic management and surveillance. The objective of this paper is to present an innovati…
We provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different, but related, target distribution. Firstly, we propose an improvement of the previous approach we proposed in Germain et al. (2013), …
To reduce the label complexity in Agnostic Active Learning (A^2 algorithm), volume-splitting splits the hypothesis edges to reduce the Vapnik-Chervonenkis (VC) dimension in version space. However, the effectiveness of volume-splitting critically depends on the initial hypothesis and this problem is also known as target…