Paper proposes a new loss function for conditional models using soft targets.
problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft-q-function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.
problem Learning variance and incorrect reference signals in deep reinforcement learning.
method t-soft update method inspired by student-t distribution, which reduces extreme updates and accelerates similar updates.
result The t-soft update method outperforms conventional methods in terms of return and variance in PyBullet robotics simulations.
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for a…
In industrial systems, certain process variables that need to be monitored for detecting faults are often difficult or impossible to measure. Soft sensor techniques are widely used to estimate such difficult-to-measure process variables from easy-to-measure ones. Soft sensor modeling requires training datasets includin…
New PL method improves ASR accuracy without pseudo-labels.
problem Improving ASR accuracy with limited labeled data.
method End-to-end continuous pseudo-labeling with soft-labels.
result Soft-labels can lead to model collapse, but regularization can mitigate this.
This work proposes a model to disentangle image factors effectively and control their manipulation.
problem Controlling disentanglement during image editing while preserving object identity.
method Encoder-decoder architecture with decorrelation regularization and soft target representations.
result The model successfully disentangles image factors and manipulates them effectively.
This paper tackles disentanglement in image editing and reconstruction.
problem Learning disentangled image representations and balancing disentanglement strength and reconstruction quality.
method Distance covariance based decorrelation regularization for disentanglement, soft target representation for reconstruction, and collapsing AE decoder and GAN generator.
result The proposed model improves the disentanglement strength and perceptual quality of generated images.
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high performance can be explained by efficient knowledge representation of deep learnin…
Proposes a new sampling policy for ranking and selection problems.
problem Improving ranking and selection in adaptive sampling policies.
method Annealed entropic allocation, using soft-min weights and saddlepoint corrections.
result Consistently competitive performance in various settings.
New approach to control diffusion processes with soft constraints.
problem Finding an optimal diffusion process with a target terminal distribution.
method Generalized Schrödinger bridge problem with soft constraints, solving for a geometric mixture of target and other distributions.
result The terminal distribution of the optimally controlled process is a geometric mixture of the target and another distribution.
New method improves stability of soft FQI for offline RL.
problem Stability issues in soft FQI under function approximation.
method Stationary reweighting to align operator norms.
result Local linear convergence proved under certain conditions.
OTSS learns personalized decision weights from logged decisions and outputs.
problem Learning context-specific decision weights from logged decisions and outputs.
method Output-targeted soft-segmentation model that deploys personalized decision-ready weight vectors.
result OTSS achieves the lowest mean regret in benchmark settings.
Proposes IFCDA framework to improve cross-domain adaptation.
problem Negative transfer and difficulty in handling category-irrelevant losses in DA.
method Importance filtered mechanism to generate filtered soft labels, combined with graph-based label propagation.
result Significantly improves performance in both Closed-Set and Open-Set DA scenarios.
A framework learns dynamic soft labels to improve model generalization and accuracy.
problem Models trained on one-hot labels overfit and are sensitive to noisy annotations.
method Proposes a framework where labels are treated as learnable parameters, adapting dynamically during optimization.
result Consistent gains across different datasets and architectures, improving ResNet18 by 2.1% on CIFAR100.
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge i…
GACBO optimizes unknown causal graphs with interventions.
problem Optimizing a target variable on an unknown causal graph with interventions.
method Graph Agnostic Causal Bayesian Optimisation (GACBO) seeks to balance exploitation and exploration of causal structures and functions.
result GACBO outperforms baselines in simulated and real-world applications.
Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.
problem Sequential budget allocation in ranking and selection
method Annealed weighted soft-min framework
result Surrogate converges uniformly to the hard minimum, soft-min weights concentrate on active challengers, and target allocation map is continuous.
Binary classification is a common statistical learning problem in which a model is estimated on a set of covariates for some outcome indicating the membership of one of two classes. In the literature, there exists a distinction between hard and soft classification. In soft classification, the conditional class probabil…
Model identifies causal structure from paired observational and interventional data with unknown soft interventions.
problem Identifying causal structure from observational and interventional data with unknown soft interventions.
method Proposes a scalable causal discovery model that aggregates subset-level PDAGs and applies contrastive cross-regime orientation rules.
result The model asymptotically recovers the identifiable PDAG and can orient additional edges compared to non-contrastive subset-restricted methods.
There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such as by adding label noise, incorporating label ambiguity or using distillation. In…
EAST aligns neural network classifiers with user-defined evaluation metrics.
problem Mismatch between neural network training and evaluation metrics leads to suboptimal performance.
method EAST uses dynamic thresholding, soft-set confusion matrix, and annealing to align neural network predictions with target evaluation metrics.
result EAST improves alignment between training objectives and evaluation metrics, outperforming existing methods.
NLE embeds labels for domain adaptation with neural networks.
problem Adapting deep neural networks with unpaired source and target domain data.
method Distill source-domain knowledge into l-vectors, soft targets for adaptation.
result 14.1% relative word error rate reduction over direct re-training.
A new method for unsupervised domain adaptation using manifold learning.
problem Leveraging rich source domain information to target domain without labeled data.
method Discriminative Manifold Embedding and Alignment framework.
result Consistent transferability and discriminability achieved through manifold metric alignment.
TT-DAC-PS: A deterministic actor-critic approach for optimal trade execution
problem Optimal execution of large stock sell programs
method Twin-Target Deterministic Actor-Critic with Policy Smoothing
result Reduces mean implementation shortfall percentage
Learning using privileged information is an attractive problem setting that helps many learning scenarios in the real world. A state-of-the-art method of Gaussian process classification (GPC) with privileged information is GPC+, which incorporates privileged information into a noise term of the likelihood. A drawback o…
Bayesian method for inferring causal relations from mixed observational and interventional data.
problem Challenges in causal inference from heterogeneous study conditions with unknown soft interventions.
method Interventional Bayesian Gaussian equivalent score for a mixture of observational and interventional data.
result Effective characterisation of posterior distributions of causal structures and intervention effects.
Proposes a framework to improve domain adaptation without labeled data.
problem Improving adaptability and preserving intrinsic data structure in unsupervised domain adaptation.
method Discriminative Manifold Propagation framework using soft labels and manifold metric alignment.
result The method achieves better transferability and discriminability compared to existing approaches.
Band-limited SAC improves learning efficiency and stability in simulated environments.
problem Improving sample efficiency and stability in SAC algorithms.
method Artificially bandlimiting the target critic's spatial resolution using a convolutional filter.
result Bandlimited SAC outperforms classic twin-critic SAC in various Gym environments and is more stable.
Rotation invariant algorithms fail with hard labels sampled from sparse targets.
problem Rotation invariant algorithms fail to learn from hard labels sampled from sparse targets.
method Proving the excess risk of rotation invariant algorithms and proposing a simple non-rotation invariant algorithm.
result Rotation invariant algorithms incur an excess risk of $Ω\left(\frac{d-1}{n}
ight)$, while non-rotation invariant algorithms have an excess risk of $O\left(\frac{s\log d}{n}
ight).
Unsupervised models can provide supplementary soft constraints to help classify new target data under the assumption that similar objects in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in a…
New method generates plausible counterfactuals for time series classification.
problem Generating realistic counterfactuals for time series data.
method Gradient-based optimization with soft-DTW alignment and multi-faceted loss function.
result Our method outperforms existing approaches in temporal realism and distributional alignment.
GAIT-prop derives a biologically plausible learning rule from backpropagation.
problem Biological implausibility in traditional backpropagation for neural networks.
method GAIT-prop uses a top-down model to convert output error into plausible targets for weight updates.
result GAIT-prop and backpropagation give identical weight updates under certain conditions.
Iterative thresholding algorithms seek to optimize a differentiable objective function over a sparsity or rank constraint by alternating between gradient steps that reduce the objective, and thresholding steps that enforce the constraint. This work examines the choice of the thresholding operator, and asks whether it i…
Compressed Federated Distillation reduces communication in federated learning.
problem Communication constraints in Federated Learning.
method Compressed Federated Distillation (CFD) leverages soft labels and quantization techniques.
result Reduces communication by more than 4 orders of magnitude compared to Federated Averaging.
Employers actively look for talents having not only specific hard skills but also various soft skills. To analyze the soft skill demands on the job market, it is important to be able to detect soft skill phrases from job advertisements automatically. However, a naive matching of soft skill phrases can lead to false pos…
Many applications in data analysis begin with a set of points in a Euclidean space that is partitioned into clusters. Common tasks then are to devise a classifier deciding which of the clusters a new point is associated to, finding outliers with respect to the clusters, or identifying the type of clustering used for th…
Soft labeling impacts OOD detection in neural networks.
problem Impact of soft labeling on OOD detection in deep neural networks.
method Empirical analysis of how soft labeling affects OOD detection performance.
result Soft labeling can either improve or deteriorate OOD detection performance.
Developed a new thresholding method that connects soft and hard thresholding.
problem Connecting soft and hard thresholding methods in data analysis.
method Scaled soft thresholding method with empirical scaling values.
result Found two sources of over-fitting in the scaled soft thresholding method.
Soft cells fill space without gaps, derived from minimal surfaces and deformed using edge bending.
problem Creating space-filling shapes without sharp corners.
method Edge bending algorithm to deform polyhedral tilings into soft tilings.
result Soft tilings derived from minimal surfaces can be continuously transformed into one another.
Motivated by applications in computational advertising and systems biology, we consider the problem of identifying the best out of several possible soft interventions at a source node V in an acyclic causal directed graph, to maximize the expected value of a target node Y (located downstream of V). Our setting im…
We use partial class memberships in soft classification to model uncertain labelling and mixtures of classes. Partial class memberships are not restricted to predictions, but may also occur in reference labels (ground truth, gold standard diagnosis) for training and validation data. Classifier performance is usually ex…
We use SMC with twist functions to improve probabilistic inference in LLMs.
problem Improving probabilistic inference in large language models.
method We use Sequential Monte Carlo with learned twist functions to estimate expected future values and focus inference on promising sequences.
result Twisted SMC improves the accuracy of language model inference and evaluation.
ASBART accelerates Soft BART for faster Bayesian regression.
problem Slow computation in Soft BART.
method Proposed ASBART, a variant of Soft BART.
result ASBART is about 10 times faster than Soft BART with similar accuracy.
Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid l…
CriticSMC improves planning efficiency in constrained environments.
problem Planning with hard constraints in dynamic environments.
method Sequential Monte Carlo with learned heuristic factors.
result CriticSMC reduces collision rates with low computational cost.
New method allows sheets to morph into multiple shapes via spatially varying stimuli.
problem Limitation of current shape-programmed sheets to achieve only one target geometry.
method Patterning the stimulus itself for spatiotemporal control over local deformation magnitudes.
result A single physical sample can be induced to traverse a continuous family of target geometries.