Paper identifies objective mismatch in MBRL, affecting control task performance.
problem Objective mismatch in MBRL framework affects control task performance.
method Proposes re-weighting dynamics model training to mitigate mismatch.
result Likelihood of one-step ahead predictions is not always correlated with control performance.
New tensor kernels reduce mismatch between clustering and reconstruction objectives in deep learning.
problem Objective Function Mismatch in deep clustering.
method Proposed Unsupervised Companion Objectives (UCOs) with tensor kernels to address mismatch.
result Reduced OFM between clustering and reconstruction objectives, leading to improved clustering performance.
New model tackles real-world distribution mismatches in machine learning.
problem Real-world applications often have training and test distributions that differ.
method Developed a learning model based on information theory using importance sampling.
result The model performs better under large distribution deviations.
The family of f-divergences is ubiquitously applied to generative modeling in order to adapt the distribution of the model to that of the data. Well-definedness of f-divergences, however, requires the distributions of the data and model to overlap completely in every time step of training. As a result, as soon as the s…
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.
A new method improves data generation quality by correcting score mismatches.
problem Score mismatch issue in conditional score-based data generation methods.
method Denoising Likelihood Score Matching (DLSM) loss for classifier training.
result The proposed method outperforms previous methods on Cifar-10 and Cifar-100 benchmarks.
This paper tackles objective inconsistency in federated optimization with heterogeneous clients.
problem Objective inconsistency due to heterogeneity in clients' datasets and computation speeds.
method General framework for analyzing federated heterogeneous optimization algorithms, including FedAvg and FedProx, and proposing FedNova.
result FedNova eliminates objective inconsistency while preserving fast error convergence.
Balanced Activation improves object detection performance on long-tailed datasets.
problem Mismatch between training and testing label distributions in object detection.
method Introduces Balanced Activation (Balanced Softmax and Balanced Sigmoid) to address label distribution shift.
result Balanced Activation provides ~3% gain in mAP on LVIS-1.0 compared to state-of-the-art methods.
Most of the existing studies on voice conversion (VC) are conducted in acoustically matched conditions between source and target signal. However, the robustness of VC methods in presence of mismatch remains unknown. In this paper, we report a comparative analysis of different VC techniques under mismatched conditions. …
New method optimizes language model performance for test-time strategies.
problem Mismatch between training objectives and test-time deployment of large language models.
method Tail-Extrapolated estimators to approximate best-of-N performance from limited training rollouts.
result Improved performance of best-of-N deployment across various models and datasets.
New state-only IL algorithm tackles MDP transition mismatch.
problem Transition dynamics mismatch between expert and imitator MDPs.
method Adversarial state-only IL with two subproblems solved iteratively.
result Effective performance improvement in transition dynamics mismatch scenarios.
We present a framework to understand GAN training as alternating density ratio estimation and approximate divergence minimization. This provides an interpretation for the mismatched GAN generator and discriminator objectives often used in practice, and explains the problem of poor sample diversity. We also derive a fam…
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
PACMAN provides bounds for classification tasks considering accuracy vs. negative log-loss mismatch.
problem Mismatch between accuracy and negative log-loss in classification tasks.
method Point-wise PAC approach over generalization gap, using likelihood ratio and concentration inequalities.
result PACMAN provides point-wise PAC bounds for the generalization problem.
We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. Howe…
Improving in-context learning for latent space Bayesian optimization by adapting pretraining on molecular latent space.
problem Improving in-context learning for latent space Bayesian optimization.
method Adapting pretraining on molecular latent space.
result Achieving strong performance on held-out molecular optimization benchmarks.
Improved BN for better performance in imbalanced data.
problem Improving classification accuracy in imbalanced datasets.
method Combining weighted loss function with modified batch normalization.
result Modified batch normalization improves classification accuracy in imbalanced datasets.
New method reduces state distribution mismatch in off-policy RL.
problem State distribution mismatch in off-policy RL algorithms.
method Develops a novel constrained off-policy gradient objective to minimize state distribution shift.
result Minimizing state distribution shift improves performance in off-policy RL algorithms.
Training a source model optimally for its own task is suboptimal for downstream transfer.
problem The optimality of a source model for its own task hinders downstream transfer performance.
method Analyzes L2-SP ridge regression, characterizes transfer-optimal source penalty, and identifies alignment-dependent effects.
result Transfer benefits from stronger source regularization when aligned imperfectly, and from weaker regularization when aligned perfectly.
Large learning rates improve kernel method performance.
problem Improving generalization in kernel methods with large learning rates.
method Analyzing the spectral decomposition of the solution to a quadratic objective in a separable Hilbert space.
result Large learning rates influence the spectral decomposition of the solution, leading to better generalization.
The methodology of community detection can be divided into two principles: imposing a network model on a given graph, or optimizing a designed objective function. The former provides guarantees on theoretical detectability but falls short when the graph is inconsistent with the underlying model. The latter is model-fre…
SONA improves conditional generation by balancing authenticity and alignment.
problem Challenges in balancing authenticity and conditional alignment in conditional generative models.
method SONA integrates unconditional discrimination, matching-aware supervision, and adaptive weighting to balance authenticity and alignment.
result SONA achieves superior sample quality and conditional alignment compared to state-of-the-art methods.
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio between clean and noisy spectra. In either case, the network is optimized by minimizi…
CADO optimizes heatmap-based solvers for cost minimization, overcoming performance limitations.
problem Heatmap-based solvers lack objective alignment for cost minimization.
method CADO uses Reinforcement Learning to optimize solution cost directly, introducing Label-Centered Reward and Hybrid Fine-Tuning.
result CADO achieves state-of-the-art performance across diverse benchmarks.
New approach tackles class imbalance in long-tailed datasets using domain adaptation techniques.
problem Class imbalance in long-tailed datasets leading to poor model performance.
method Proposes a meta-learning approach to estimate differences between class-conditioned distributions.
result Validated approach on six benchmark datasets and three loss functions.
Learning reward functions can lead to poor policy performance despite low error.
problem Low error in learned reward functions does not guarantee low regret in policy performance.
method Mathematical analysis of reward learning and policy optimization.
result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.
New algorithm reduces performance loss in IRL with mismatched transition dynamics.
problem Performance degradation in inverse reinforcement learning due to mismatched transition dynamics.
method Proposed a robust Maximum Causal Entropy (MCE) IRL algorithm leveraging robust reinforcement learning insights.
result Empirically demonstrated stable performance improvement under transition dynamics mismatches.
We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of state-of-the-art methods based on key elements of this framework: gradient estimation, value prediction, and optimization landscapes. Our result…
New insights into how to inspect and learn from multi-stage processes and AI reasoning.
problem Understanding how to attribute outcomes to early stages in multi-stage operations and AI reasoning.
method Information-theoretic analysis and mathematical proofs of four key results.
result Uniform checkpoint spacing is minimax-optimal for inspection design under homogeneous signal attenuation.
A new BN method corrects size mismatch in WLF for imbalanced data.
problem Learning from imbalanced datasets in neural networks.
method Proposes weighted batch normalization (WBN) to correct size mismatch between BN and WLF.
result WBN corrects size mismatch and improves classification performance in imbalanced datasets.
Improved RL algorithm for robustness against parameter mismatches.
problem Learning robust control policies against parameter mismatches between training and testing environments.
method Formulated as DR-RL problem, proposed RPVL algorithm for tabular episodic learning with four divergences.
result Achieved ildeO(∣S∣∣A∣H5) sample complexity uniformly better than existing results. SURF steers scalarization weights to uniformly traverse the Pareto front.
problem Non-uniform coverage of the Pareto front when using scalarization weights.
method Geometric analysis and CDF mapping to select weights for uniform coverage.
result SURF converges to uniform Pareto front coverage under provable conditions.
The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.
problem Theoretical guarantees for score-mismatched diffusion models in zero-shot conditional sampling.
method Theoretical analysis of score-mismatched diffusion models and zero-shot conditional samplers.
result Theoretical performance guarantees with explicit dimensional dependencies for score-mismatched diffusion samplers.
We investigated the impact of noisy linguistic features on the performance of a Japanese speech synthesis system based on neural network that uses WaveNet vocoder. We compared an ideal system that uses manually corrected linguistic features including phoneme and prosodic information in training and test sets against a …
AdaGrad fails to adapt to Hölder-smoothness in composite optimization problems.
problem AdaGrad's convergence rate is suboptimal for composite objectives.
method Exhibited a simple one-dimensional convex problem to highlight AdaGrad's limitations.
result AdaGrad does not achieve the classical convergence rate for Hölder-smooth objectives.
New similarity measure for covariate shift improves nonparametric regression rates.
problem Improving nonparametric regression under covariate shift.
method Introducing a new similarity measure based on probability ratios.
result Shows a sharper rate of convergence compared to transfer exponent.
We propose a simple neural network model to deal with the domain adaptation problem in object recognition. Our model incorporates the Maximum Mean Discrepancy (MMD) measure as a regularization in the supervised learning to reduce the distribution mismatch between the source and target domains in the latent space. From …
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
CycleFQI tackles offline reinforcement learning for cyclic MDPs, mitigating state distribution mismatch.
problem Offline reinforcement learning for cyclic MDPs with heterogeneous dynamics and discount factors.
method CycleFQI decomposes the cyclic process into stage-wise sub-problems, using vector of stage-specific Q-functions.
result CycleFQI mitigates the curse of dimensionality and provides finite-sample suboptimality error bounds.
Laplace kernel feature selection offers statistical guarantees for nonparametric models with few samples.
problem Statistical guarantees for kernel-based feature selection in nonconvex optimization problems.
method Sharp characterization of the gradient of the objective function for Laplace kernel feature selection.
result Model-selection consistency for Laplace kernel-based feature selection in nonparametric settings with n∼logp samples. ITF improves DSR but inflates curvature, while marginal likelihood reduces it, affecting QoIs.
problem Curvature mismatch between teacher forcing and marginal likelihood in chaotic dynamical systems.
method Comparing objective-induced curvatures of ITF and marginal likelihood in a probabilistic switching augmentation of AL-RNNs.
result Curvature inflation by ITF and reduction by marginal likelihood affect dynamical quantities of interest.
New method addresses error bounds for PnP-ULA under mismatched models.
problem Error bounds for PnP-ULA under mismatched measurement and prior models.
method Posterior-L2 pseudometric to quantify error bounds.
result Explicit error bound for PnP-ULA under mismatched posterior distribution.
Paper addresses linear regression with partially mismatched data using local search with theoretical guarantees.
problem Linear regression with partially mismatched data.
method Optimization formulation and greedy local search algorithm with theoretical guarantees.
result Local search algorithm converges to nearly-optimal solution at a linear rate under certain conditions.
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to voco…
Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e.g., word error rate (WER). This results in a mismatch…
Study on LMMSE estimation with model mismatch, quantifying MSE trade-offs.
problem Model mismatch in LMMSE estimation with undermodeling.
method Analyzing the average MSE of LMMSE estimation with random regressors.
result Performance improvement depends on sufficient samples and model complexity.
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a comp…
AdvAs improves GAN training by penalizing the generator based on discriminator gradients.
problem Mismatch between theoretical analysis and practice in GAN training.
method AdvAs is a penalty imposed on the generator based on the discriminator's gradient norm.
result AdvAs reduces the mismatch between theory and practice and improves GAN training.