Self-training improves gradual domain adaptation with unlabeled data.
problem Improving machine learning models' adaptability to gradually shifting data distributions.
method Proved upper bounds on self-training error, highlighted the importance of regularization and label sharpening, and demonstrated algorithmic insights.
result Self-training works well for gradual shifts, especially with small Wasserstein-infinity distance.
A new method uses normalizing flows for gradual domain adaptation.
problem Difficulty in domain adaptation when source and target domains have a large gap.
method Proposes using normalizing flows to learn a transformation from target to Gaussian mixture distribution.
result Improves classification performance and mitigates the problem of gradual self-training failure.
A cost-effective framework for gradual domain adaptation using multifidelity.
problem Degrading prediction performance due to large domain distance.
method Combines multifidelity and active domain adaptation.
result Improves prediction performance with reduced sample cost.
Gradual domain adaptation improves model transfer between domains with intermediate training.
problem Challenges in unsupervised domain adaptation when distribution shifts are large.
method Gradual self-training using intermediate domains along the Wasserstein geodesic.
result GOAT framework generates intermediate domains for improved adaptation.
Improved analysis of gradual domain adaptation with better generalization bounds.
problem Improving generalization in target domain through intermediate unlabeled domains.
method Analyzed gradual self-training under more general assumptions, proving a new generalization bound.
result Proved a significantly improved generalization bound of ε0 + O(TΔ + T/√n) + ˜O(1/√nT).
The paper tackles gradual domain adaptation with manifold-constrained DRO, showing error bounds across distributions.
problem Gradual domain adaptation challenge with manifold-constrained data distributions.
method Distributionally Robust Optimization (DRO) with an adaptive Wasserstein radius.
result Theoretical bounds on classification error across distributions, demonstrating error propagation dynamics.
New algorithm for nonstationary multi-armed bandits with optimal performance.
problem Nonstationary multi-armed bandits with changing model parameters over time.
method Adaptive Resetting Bandit (ADR-bandit) algorithm using adaptive windowing techniques.
result ADR-bandit achieves nearly optimal performance in both abrupt and gradual changes.
BRPC online Bayesian calibration handles gradual and abrupt system changes.
problem Aligning model outputs with field observations in evolving systems.
method Bayesian Recursive Projected Calibration (BRPC) for streaming data under simulator mismatch and nonstationarity.
result Improves calibration accuracy under gradual changes and robustness under abrupt regime shifts.
New algorithm for ML models in gradually adapting data settings.
problem Training models when data distribution reacts to the model over time.
method Stateful Performative Gradient Descent (Stateful PerfGD)
result Stateful PerfGD minimizes performative loss in gradually adapting data settings.
Large batch training improves deep learning performance without needing warmup.
problem Slow convergence at early epochs in large batch training.
method Proposes CLARS algorithm and analyzes convergence rate.
result Proposed algorithm outperforms gradual warmup and state-of-the-art large-batch optimizers.
Motivated by the problem of tuning hyperparameters in machine learning, we present a new approach for gradually and adaptively optimizing an unknown function using estimated gradients. We validate the empirical performance of the proposed idea on both low and high dimensional problems. The experimental results demonstr…
New model detects gradual changes in processes more accurately.
problem Traditional change-point models fail to identify gradual changes effectively.
method Introduces a Bayesian change-dynamic model using hierarchical models for gradual change detection.
result The model identifies gradual changes faster and more accurately than traditional models.
Scales gradual pattern discovery from imprecise data.
problem Managing large collections of gradual patterns from imprecise data.
method Introduces gradualness thresholds and considers attribute value distribution.
result Eliminates noise patterns, showing a smaller set of meaningful patterns.
An adaptive dropout approach improves high-dimensional Bayesian optimization.
problem High-dimensional black-box optimization problems.
method Adaptive dropout of variables in the acquisition function.
result AdaDropout effectively tackles high-dimensional challenges and improves solution quality.
Gradually Truncated Log-normal distribution - Size distribution of firms Abstract Many natural and economical phenomena are described through power law or log- normal distributions. In these cases, probability decreases very slowly with step size compared to normal distribution. Thus it is essential to cut-off these di…
Cost-efficient distributed learning via combinatorial bandits.
problem Trade-off between error and runtime in distributed SGD.
method Combinatorial multi-armed bandit model to learn fastest workers.
result Significantly lower errors with same computational efforts and less communication.
Meta-SAGE improves deep RL scalability for CO tasks by adapting pre-trained models to larger-scale problems.
problem Improving scalability of deep reinforcement learning models for combinatorial optimization tasks.
method Meta-SAGE combines a scale meta-learner and scheduled adaptation with guided exploration to adjust model parameters for larger-scale problems.
result Meta-SAGE outperforms previous methods and significantly improves scalability in CO tasks.
IUPM monitors machine learning models under gradual shifts using optimal transport and active labeling.
problem Gradual distribution shifts lead to unnoticed accuracy declines in machine learning models.
method Incremental Uncertainty-aware Performance Monitoring (IUPM) using optimal transport and active labeling.
result IUPM outperforms existing baselines in gradual shift scenarios and guides label acquisition more effectively.
Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the training distribution shifts, the network is slow to adapt, and when it does adapt…
Paper proposes an unsupervised adaptation algorithm for non-stationary batch data.
problem Gradual concept drift in non-stationary data sources.
method Iterative unsupervised algorithm for model adaptation.
result Improved performance of adapted models compared to unadapted ones.
STAD adapts models to evolving time-based data shifts.
problem Gradual distribution shifts over time challenge existing test-time adaptation methods.
method Bayesian filtering method that learns time-varying dynamics in hidden features.
result STAD excels in handling small batch sizes and label shift on real-world data.
Paper proposes an adaptive gradient method for federated learning.
problem Communication efficiency in federated learning.
method Adaptive gradient method for federated learning.
result Guaranteed convergence and communication efficiency in federated learning.
This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.
problem Balancing accuracy, efficiency, and robustness in neural networks with limited resources.
method Adversarial pruning with a cutoff-scale strategy to dynamically adjust the strength of adversarial examples.
result Blind adversarial pruning improves the overall AER of pruned models compared to adversarial pruning.
American options in a multi-asset market model with proportional transaction costs are studied in the case when the holder of an option is able to exercise it gradually at a so-called mixed (randomised) stopping time. The introduction of gradual exercise leads to tighter bounds on the option price when compared to the …
A fundamental issue for statistical classification models in a streaming environment is that the joint distribution between predictor and response variables changes over time (a phenomenon also known as concept drifts), such that their classification performance deteriorates dramatically. In this paper, we first presen…
Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data.…
The state-of-the-art solutions for Aspect-Level Sentiment Analysis (ALSA) were built on a variety of deep neural networks (DNN), whose efficacy depends on large amounts of accurately labeled training data. Unfortunately, high-quality labeled training data usually require expensive manual work, and may thus not be readi…
PAS method improves UDA by progressively refining subspaces for reliable pseudo-labels.
problem Mitigating mode collapse in unsupervised domain adaptation.
method Progressive Adaptation of Subspaces (PAS) approach.
result PAS effectively mitigates mode collapse and improves performance in UDA and PDA.
Adaptive sampling method solves constrained and composite optimization problems.
problem Solving constrained optimization problems with stochastic objectives and deterministic constraints.
method Proximal gradient method with adaptive sampling to improve gradient approximation quality.
result Convergence results established for both strongly convex and general convex objectives.
GROVER improves word representations by gradually adding random noises during training.
problem Improving word representations for better model performance.
method Gradually adding random noises to word embeddings during training.
result GROVER improves model performances on most text classification datasets.
Paper proposes a method to design molecules with specific properties.
problem Designing molecules with desired chemical and biological properties.
method Energy-based model in latent space, SGDS algorithm for gradual distribution shifting.
result Method achieves strong performances on various molecule design tasks.
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…
This paper describes audEERING's submissions as well as additional evaluations for the One-Minute-Gradual (OMG) emotion recognition challenge. We provide the results for audio and video processing on subject (in)dependent evaluations. On the provided Development set, we achieved 0.343 Concordance Correlation Coefficien…
Domain adaptation is essential to enable wide usage of deep learning based networks trained using large labeled datasets. Adversarial learning based techniques have shown their utility towards solving this problem using a discriminator that ensures source and target distributions are close. However, here we suggest tha…
Adaptive multi-stage density ratio estimation improves learning of latent space EBM.
problem Learning energy-based models in latent space is computationally expensive and challenging.
method Adaptive multi-stage density ratio estimation using NCE to bridge the gap between prior and posterior densities.
result The method enables more expressive prior models and sharpens the latent space EBM.
Paper detects gradual changes in cluster structure using MC fusion.
problem Detecting gradual changes in cluster structure over time.
method MC fusion for multiple mixture numbers, examining MC transition.
result Accurately captures cluster structure during transitional periods.
Game (Israeli) options in a multi-asset market model with proportional transaction costs are studied in the case when the buyer is allowed to exercise the option and the seller has the right to cancel the option gradually at a mixed (or randomised) stopping time, rather than instantly at an ordinary stopping time. Allo…
Improves FI-PINNs by combining re-sampling and subset simulation for better failure probability estimation.
problem Estimating failure probability in physics-informed neural networks (PINNs).
method Adaptive sampling with re-sampling and subset simulation, using cosine-annealing for uniform to adaptive transition.
result Significant improvement in estimating failure probability and generating new training points in the failure region.
Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Rec…
A TTA framework improves forecasting accuracy in non-stationary time series.
problem Improving forecasting accuracy in non-stationary time series.
method Normalization-based test-time adaptation for causal timeseries forecasting and direction classification.
result Normalization-based TTA improves forecasting error in synthetic gradual drift and can even hurt in aggressive norm-only adaptation in financial markets.
Proposes a method to improve SLMC for multimodal distributions.
problem Difficulty of applying SLMC to multimodal distributions.
method Parallel adaptive annealing with VAE-SLMC.
result Can proficiently obtain accurate samples from multimodal distributions.
SALSA automatically adjusts learning rates in stochastic gradient methods.
problem Automatic adjustment of learning rates in stochastic gradient methods.
method SALSA uses a line-search procedure to gradually increase the learning rate, then a statistical test to decrease it.
result SALSA matches the performance of best hand-tuned learning rate schedules in deep learning tasks.
Recently, Factorization Machines (FM) has become more and more popular for recommendation systems, due to its effectiveness in finding informative interactions between features. Usually, the weights for the interactions is learnt as a low rank weight matrix, which is formulated as an inner product of two low rank matri…
Paper tackles cold-start domain adaptation with language descriptions.
problem Cold-start domain adaptation failure with scarce target data.
method Leverages textual descriptions to learn preferences from LLM, integrates into EM algorithm.
result Framework guides source selection for weak target signals, improves as data accumulates.
Adaptive portfolio outperforms static alternatives by 120% over 5 years.
problem Achieving strong and stable long-term performance in diversified portfolios.
method RL-BHRP: A two-level, learning-based approach that adjusts sector and stock exposures dynamically.
result Adaptive portfolio outperforms static alternatives by 120% over 5 years.
New concept of mixture complexity helps detect gradual clustering changes.
problem Determining the number of clusters in mixture models with overlaps and weight biases.
method Introducing mixture complexity (MC) as a new measure of cluster size, defined from information theory.
result MC can detect gradual clustering changes, allowing earlier detection and finer distinction.
Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregat…
Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.