Unified framework for speaker-adaptive models using scaling and bias codes.
problem Improving speaker-adaptive neural-network based speech synthesis systems.
method Unified framework representation and generalized scaling and bias codes.
result Improves performance of speaker adaptation compared to conventional methods.
The paper improves generalization bounds for domain adaptation.
problem Improving generalization bounds for domain adaptation under practical conditions.
method Derives generalization bounds for domain adaptation based on finitely many moments and smoothness conditions.
result Obtains generalization bounds for domain adaptation.
New method adapts without backprop, faster and better.
problem Efficient domain adaptation without source data.
method Computing class prototypes from pre-trained model.
result Significant accuracy improvements over pre-trained model.
Paper defines adapted generating sets and bases for Riemann surfaces.
problem Understanding conformal automorphism groups on compact Riemann surfaces.
method Definition and existence proof of adapted generating sets and bases.
result Existence of adapted generating sets and bases for any conformal group.
Seq2seq ASR adapts to speakers, improving performance by 25%.
problem Speaker adaptation for seq2seq ASR systems to match conventional methods.
method Applied Kullback-Leibler divergence and Linear Hidden Network adaptation to seq2seq models.
result 25% relative word error rate improvement with seq2seq model adaptation.
Paper presents a Transformer model for automatic domain adaptation.
problem Challenges in selecting or designing domain adaptation algorithms.
method Transformer model approximates and selects domain adaptation algorithms.
result Transformers can approximate and automatically select domain adaptation algorithms.
Adaptive region-based active learning seeks labels for complex data.
problem Efficiently label complex datasets with minimal human effort.
method Adaptive region partitioning and active learning for distinct predictors.
result Substantial empirical benefits over existing methods.
Efficient EKF-based algorithm improves LSTM adaptive learning accuracy.
problem Improving accuracy of LSTM-based adaptive learning.
method Extended Kalman filter (EKF) based second-order training algorithm.
result 10 to 45% improvement in accuracy compared to state-of-the-art methods.
FLoE adapts LLMs by selectively deploying LoRA adapters based on layer importance and task requirements.
problem Uniform LoRA deployment across all layers leads to inefficient and redundant parameter allocation.
method FLoE uses Fisher information to dynamically identify task-critical layers and optimizes LoRA ranks.
result FLoE achieves significant efficiency-accuracy trade-offs, especially in resource-constrained environments.
New model-based methods adapt pre-trained policies to unseen environments efficiently.
problem High sample complexity in reinforcement learning limits practical applications.
method Combines online learning and adaptive control to adapt policies in unseen environments.
result Proves policies can quickly recover trajectories from source to target environments.
Develops a generic two-layer framework for adaptive ABMs.
problem Bi-level adaptation problem in ABMs: agents adapt to environment, and environment adapts to agents.
method Formalizes bi-level problem as a Stackelberg game with conditional policies, solving coupled non-linear equations.
result Unified framework for adaptive ABMs, addressing traditional ABM limitations.
This review categorizes domain adaptation methods without target labels.
problem How to train a classifier from a source domain to generalize to a target domain.
method Sample-based, feature-based, and inference-based methods.
result Recurring ideas and conditions for cross-domain generalization error.
Memory-based adaptation speeds up neural network learning.
problem Slow adaptation of neural networks to changing data.
method Stores examples in memory and uses context-based lookup to modify weights.
result Higher learning rates lead to better performance on new data.
Generative models learn better with data-adaptive noise.
problem Learning heavy-tailed distributions in flow-based models.
method Data-adaptive latent noise using 1D quantile functions optimized via Wasserstein distance.
result Flexibility and effectiveness in learning heavy-tailed and compactly supported distributions.
Gradient learning optimises MCMC proposal distributions.
problem Intractable targets in MCMC sampling.
method Gradient-based optimisation of proposal distributions using a maximum entropy regularised objective function.
result Our method can outperform traditional MCMC algorithms, including Hamiltonian Monte Carlo.
Paper proposes adaptive parameter selection for KGD algorithms.
problem Improving parameter selection for kernel-based gradient descent.
method Integrates bias-variance analysis with splitting method, introduces empirical effective dimension.
result Adaptive parameter selection strategy achieves optimal generalization error bound.
Adaptive discretization improves model-based RL in large spaces.
problem Efficient model-based reinforcement learning in large state-action spaces.
method Optimistic one-step value iteration with adaptive discretization.
result Adaptive discretization leads to better performance and lower memory usage.
This thesis studies domain adaptation under minimal distribution similarity assumptions using moments.
problem Learning from samples with distributions different from training samples.
method Uses minimal similarity assumptions modeled by moments.
result Establishes learning bounds and algorithms for domain adaptation.
Adaptive rule improves kernel-based gradient descent performance.
problem Improving convergence speed of kernel-based gradient descent algorithms.
method Empirical effective dimension for stopping rule, learning theory analysis, integral operator approach.
result Optimal learning rates and iteration bounds for KGD with adaptive stopping rule.
Paper proposes an improved domain adaptation technique using class-based information.
problem Adapting classifiers across domains with labeled source and unlabeled target datasets.
method Adversarial discriminator approach informed by class structure in source dataset.
result State-of-the-art results achieved on benchmark datasets.
Bayesian approach improves speech recognition with limited speaker data.
problem Reduces mismatch between training and evaluation data due to speaker differences.
method Bayesian learning for DNN adaptation models with limited speaker data.
result Bayesian adaptation consistently outperforms deterministic methods, reducing word error rates up to 1.4%.
Study shows rates for Laplacian-eigenmap methods in nonparametric regression.
problem Minimizing error in nonparametric regression using Laplacian-eigenmap.
method Adaptive and non-adaptive minimax rates using Sobolev space constraints.
result Extends minimax rates to various weighted Laplacian matrices.
Improved speech recognition with cumulative adaptation methods.
problem Robust speech recognition in varying environments and speakers.
method Used a bidirectional LSTM neural network and i-vectors for adaptation.
result Achieved 13% relative improvement in word error rate.
In this paper, we consider adaptive decision-making problems for stochastic state estimation with partial observations. First, we introduce the concept of weak adaptive submodularity, a generalization of adaptive submodularity, which has found great success in solving challenging adaptive state estimation problems. The…
Improved privacy and utility in machine learning with adaptive differential privacy.
problem Enhancing privacy in machine learning models while maintaining utility.
method Adaptive differentially private (ADP) learning method that optimally adapts noise to stepsize.
result ADP method significantly improves utility compared to standard differentially private methods.
Optimism-based methods improve adaptive regulation of linear-quadratic systems.
problem Trade-off between identifying unknown dynamics and regulating the system.
method Optimism-based adaptive policies that favor optimistic approximations of true parameters.
result Established high probability upper bounds for worst-case regret of optimism-based adaptive policies.
New RL algorithms adapt to time limits, improving task performance.
problem Fixed RL behaviors cannot adapt to different time restrictions.
method Introduced two algorithms for time adaptive RL: Independent Gamma-Ensemble and n-Step Ensemble.
result Zero-shot adaptation between different time restrictions.
New algorithm reduces adaptive regret without projections.
problem Computational expense of projections in online convex optimization.
method Lazy gradient-based algorithm with set-membership computations.
result Near-optimal adaptive regret bounds for general convex functions.
This work proves convergence of adaptive resampling for random Fourier features.
problem Sampling Fourier frequencies well for high-dimensional data.
method Data adaptive resampling of Fourier frequencies, asymptotically optimal.
result Proves convergence of adaptive resampling method for regression and classification problems.
AdamCB optimizes neural network training by adaptively selecting samples.
problem Inefficient convergence due to unequal influence of different data samples.
method Integrates combinatorial bandit techniques into Adam to adaptively select samples.
result AdamCB achieves faster convergence and better performance than existing methods.
DADAM optimizes distributed adaptive learning with low communication costs.
problem High communication costs in parallelizing adaptive gradient methods.
method Consensus-based distributed adaptive moment estimation method.
result Outperforms centralized adaptive algorithms for certain loss functions.
Bayesian approach improves AdaLoRA's performance and efficiency.
problem Improving the efficiency and performance of adaptive low-rank adaptation.
method Utilized Bayesian metrics and the Improved Variational Online Newton (IVON) optimizer for adaptive parameter budget allocation.
result Bayesian counterpart outperforms sensitivity-based importance metric and is faster than AdaLoRA.
New method improves Bayesian cross-validation.
problem Finding good proposal distributions for importance sampling.
method Implicitly adaptive importance sampling that iteratively matches moments.
result Better than many existing parametric adaptive importance sampling methods.
Paper bridges theory and algorithm for domain adaptation.
problem Domain adaptation from theory to algorithm gap.
method Extended domain adaptation theories, introduced Margin Disparity Discrepancy, and transformed into adversarial learning algorithm.
result Empirical studies show state-of-the-art accuracies on domain adaptation tasks.
Adaptive vehicle trajectory prediction for safer autonomous driving.
problem Inability of current methods to guarantee physical feasibility and adapt to human driving policies.
method Bayesian recurrent neural network combining policy and physical models, with gradient-based training and parameter adaptation.
result The proposed method ensures physical feasibility and adaptability to human driving policies.
Reinforcement learning improves wireless systems' rate adaptation.
problem Optimizing rate adaptation in 4G/5G systems using ACK/NACK feedback.
method Formulated as a Multi-Armed Bandit problem, proposed binary search algorithm with PAC guarantees.
result Achieved PAC solution for OLLA with binary search, outperforming UCB methods.
LALR adapts learning rate for faster convergence in regression and neural nets.
problem Finding optimal learning rates for faster convergence in regression and neural networks.
method Lipschitz continuity theory applied to Mean Absolute Error and Quantile loss functions.
result Adaptive learning rate policy enables up to 20x faster convergence.
GIST adapts HMC by tuning parameters based on position and momentum.
problem Locally adaptive sampling in Hamiltonian Monte Carlo.
method GIST uses Gibbs sampling to adaptively tune HMC parameters.
result GIST improves sampling efficiency for high-dimensional models.
New adaptive filters reduce energy consumption in electronic devices.
problem Reducing energy consumption in adaptive filtering algorithms.
method Data-selective adaptive filters, set-membership (SM) filters, trinion and quaternion systems, partial-updating, LMS and recursive LMS algorithms.
result Improved adaptive filtering algorithms with reduced computational complexity and enhanced stability.
Efficient CF approach using fast adaptive PCA for recommender systems.
problem Matrix completion problem in recommender systems.
method Fast adaptive randomized singular value decomposition (SVD) and termination mechanism for latent factors.
result The approach achieves near optimal prediction accuracy with high runtime efficiency.
An adaptive clustering algorithm learns from evolving data without manual tuning.
problem Clustering in dynamic data environments where distributions change over time.
method ART-based topological clustering with self-adjusting vigilance parameter.
result The algorithm outperforms state-of-the-art methods in clustering performance and continual learning.
HireVAE adapts to market regimes for online stock prediction.
problem Building an online and adaptive factor model for stock prediction.
method HireVAE uses a hierarchical latent space to estimate latent factors from historical market information.
result HireVAE outperforms previous methods in active returns across benchmarks.
This paper improves OMP-based sparse subspace clustering with data-adaptive capability.
problem Existing OMP-based approaches lack data adaptiveness, leading to inaccurate data representation.
method Develops a parameter selection process to adjust OMP parameters based on data distribution and introduces a new SEA ratio metric.
result Proposed approach achieves better clustering accuracy, SEA ratio, and representation quality compared to other OMP-based methods.
Proposes a curriculum-based dropout discriminator for domain adaptation.
problem Improving domain adaptation using deep learning networks trained on large labeled datasets.
method Introduces a curriculum-based dropout discriminator that gradually increases sample variance and uses reverse gradients to align source and target feature representations.
result The proposed model outperforms state-of-the-art results in domain adaptation tasks.
CORAL+ adapts PLDA for unsupervised domain adaptation.
problem Domain mismatch in speaker recognition systems.
method Inspired by CORAL, unsupervised PLDA adaptation.
result Improves PLDA performance on unlabeled in-domain data.
Proposes a label propagation framework for domain adaptation.
problem Subpopulation shift in machine learning domains.
method Label propagation based on a teacher classifier trained on source domain.
result End-to-end finite-sample guarantees on domain adaptation algorithm.
Adaptive feature extraction boosts contextual bandit performance.
problem Improving performance in online decision making with contextual bandit.
method Adaptive feature extraction based on online clustering and online selection of encoders.
result Clear advantages over standard contextual bandit in various environments.
Paper presents a fast and adaptive filter for SI suppression in full-duplex transceivers.
problem Self-interference suppression in full-duplex transceivers with nonlinearity.
method Adaptive projected subgradient method (APSM) in a reproducing kernel Hilbert space (RKHS).
result The proposed method achieves favorable digital SIC performance compared to benchmarks.