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.
PUDLE method analyzes and improves unrolled sparse coding networks for dictionary learning.
problem Dictionary learning problem, representing data as a combination of few atoms.
method PUDLE method addresses challenges in unrolled sparse coding networks through theoretical analysis and practical strategies.
result PUDLE method provides conditions for recovering and preserving the support of the latent code, and resolves bias and instability issues.
The study reveals simplicity bias in neural networks leading to better compositional mappings.
problem Understanding when and how to encourage neural networks to learn compositional mappings.
method Examined compositional mappings through coding length and gradient descent dynamics.
result Neural networks tend to learn the simplest bijections, explaining their good generalization.
New method reduces gender bias in language models without harming performance.
problem Bias in language models learned from biased data.
method Causal analysis to identify problematic model components, followed by linear projection of weight matrices.
result DAMA significantly decreases bias in language models while maintaining performance.
New method detects and mitigates historical bias in data.
problem Detecting and explaining historical bias in data.
method Developed a sample bias criterion and algorithms to measure and counter sample bias.
result Derived bias score provides sample-level attribution and explanation of historical bias.
Study reveals statistical bias in dataset replication, reducing accuracy drop from 11-14% to 3.6%.
problem Statistical bias in dataset replication affects model generalization accuracy.
method Analyzed ImageNet-v2, identified and corrected for bias, and compared results.
result Correcting bias reduces accuracy drop from 11-14% to 3.6%.
Study quantifies reproducibility of machine learning papers.
problem Lack of empirical reproducibility metrics in machine learning.
method Manual implementation of 255 papers from 1984-2017, analyzing features and results.
result Manual implementation revealed discrepancies between papers and their descriptions.
Improves CNN robustness by reducing texture bias.
problem CNNs' reliance on local texture over global shape.
method Inspired by human vision, InfoDrop decorrelates model output from local texture.
result Enhanced robustness across various scenarios.
GRASP removes spurious correlations in fine-tuned models, improving task performance and reducing bias.
problem Fine-tuned models can latch onto spurious correlations, leading to bias and reduced generalization.
method GRASP identifies and removes spurious correlations from model weights without removing latent factors.
result GRASP significantly reduces bias and improves task performance in various fine-tuning tasks.
This work investigates implicit bias in multiclass separable data using a novel geometry-aware optimizer.
problem Understanding implicit bias in overparameterized models on multiclass separable data.
method Introduces NucGD, a geometry-aware optimizer enforcing low-rank structures through nuclear norm constraints.
result NucGD enables scalable training and characterizes the impact of stochastic optimization dynamics.
Study improves statistical power for detecting algorithmic bias in educational data.
problem Challenges in measuring algorithmic bias using ABROCA due to skewed distribution.
method Investigates ABROCA's distributional properties and proposes nonparametric randomization tests.
result ABROCA-based bias assessments are underpowered in typical EDM sample sizes.
Paper proposes a novel approach to improve spatiotemporal precipitation forecasts.
problem Improving accuracy of spatiotemporal precipitation forecasts for flood damage mitigation.
method Introduces a rain-code fusion approach using ConvLSTM and multi-frame fusion for spatiotemporal precipitation code-to-code forecasting.
result Demonstrates enhanced accuracy in precipitation forecasts beyond 3 timesteps using the rain-code fusion.
LatentNN corrects neural network attenuation bias in astronomical data.
problem Neural networks underestimate extreme values due to measurement errors.
method Jointly optimizes network parameters and latent input values.
result LatentNN reduces attenuation bias across various signal-to-noise ratios.
AEN-SAEs address feature starvation in sparse autoencoders by stabilizing the geometric alignment of sparse coding.
problem Feature starvation in sparse autoencoders, leading to unstable and misaligned representations.
method Adaptive Elastic Net SAEs (AEN-SAEs) combine ℓ2 and ℓ1 terms to stabilize the sparse coding map and control feature interactions. result AEN-SAEs mitigate feature starvation without heuristic resampling, maintaining competitive reconstruction abilities.
Look-Ahead-Bench evaluates financial LLMs for lookahead bias, revealing significant differences in model performance.
problem Measuring and mitigating lookahead bias in financial LLMs.
method Standardized benchmark evaluating model behavior in practical financial scenarios, analyzing performance decay across market regimes.
result Standard LLMs exhibit significant lookahead bias, while Pitinf models show improved generalization and reasoning abilities.
Study evaluates bias mitigation methods in deep learning, finds they often exploit hidden biases.
problem Deep learning systems learn biases, affecting performance on minority groups.
method Improved evaluation protocol, new dataset, robustness across different tuning distributions.
result Bias mitigation methods often exploit hidden biases, are not robust to multiple forms of bias, and are sensitive to tuning set choice.
A new neural sequence prediction method using error-correcting codes improves accuracy and convergence.
problem Improving neural sequence prediction accuracy and speed.
method Error-correcting output codes, separable code maximization, latent variable mixture sampling.
result Consistent improvements on language modeling datasets and text generation tasks.
Develops Austen plots for assessing bias from unobserved confounding in observational studies.
problem Bias in causal estimates due to unobserved confounding.
method Formalizes confounding strength, uses Austen plots to visualize and quantify bias.
result Allows domain experts to assess the plausibility of strong confounders.
Paper proposes neural network for LDPC coded DCO-OFDM with clipping distortion.
problem Mitigating nonlinear clipping distortion in LDPC coded DCO-OFDM systems.
method Designs a neural network-aided bit-interleaved coded modulation (NN-BICM) receiver to improve log-likelihood ratio (LLR) through backpropagation training.
result Neural network-aided receiver achieves noticeable performance gains over other methods.
Noise in SGD affects overparameterized models, favoring sparse solutions.
problem Understanding and mitigating implicit bias in SGD with parameter-dependent noise.
method Theoretical analysis of a quadratically-parameterized model with label noise and Gaussian noise.
result SGD with label noise recovers sparse ground-truth solutions, while SGD with Gaussian noise overfits dense solutions.
CFR-Pro enhances treatment effect estimation by incorporating local proximity.
problem Treatment selection bias in HTE estimation from observational data.
method Proximity-enhanced CounterFactual Regression (CFR-Pro) with pair-wise proximity regularizer and subspace projector.
result Significantly outperforms competitors in HTE estimation accuracy.
New method discourages models from using bias shortcuts for better generalization.
problem Training models on biased data can lead to poor generalization when bias shifts.
method Train a de-biased representation by encouraging it to differ from biased representations.
result Improved generalization across synthetic and real-world biases.
Paper optimizes hyperspherical prototypes for better class separation.
problem Previous HPL approaches either lack principled optimisation or are limited to one latent dimension.
method Develops a principled optimisation procedure and uses linear block codes to create well-separated prototypes in various dimensions.
result Optimal prototype placement is characterized with achievable and converse bounds, showing near-optimality.
sgboost reduces variable selection bias in boosting with balanced group selection.
problem Reduces variable selection bias in boosting algorithms.
method Simulation-based approach to balance selection frequencies of base-learners.
result Demonstrates efficacy through simulations and flexible group variable selection.
Algorithm recovers causal graphs in presence of latent confounders and selection bias.
problem Recovering causal graphs in the presence of latent confounders and selection bias.
method Iterative causal discovery (ICD) algorithm that relies on causal Markov and faithfulness assumptions.
result Sound and complete algorithm that recovers the equivalence class of the underlying causal graph.
Transformers are less sensitive to input perturbations compared to other models.
problem Understanding the inductive biases of transformers and distinguishing them from other architectures.
method Identified token-wise sensitivity as a metric to explain transformers' inductive biases across different data modalities.
result Transformers have lower sensitivity than MLPs, CNNs, ConvMixers, and LSTMs, across vision and language tasks.
Improved disentanglement through learned feature aggregation.
problem Disentangling latent factors in images.
method Variational autoencoder trained on regionally aggregated feature maps from ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
IDF++ improves integer discrete flows for lossless compression.
problem Theoretical limitations of integer discrete flows for lossless compression.
method Investigated and improved integer discrete flows, addressing gradient bias and architecture modifications.
result Different architecture modifications improve integer discrete flows for lossless compression.
PLIT identifies plant lncRNAs from RNA-seq data with high accuracy.
problem Inaccurate identification of lncRNAs in plant transcriptomic datasets.
method PLIT uses L1 regularization and iRF classification to select optimal features from sequence and codon-bias data.
result PLIT outperforms existing CPC tools in identifying lncRNAs in plant RNA-seq datasets.
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.
GNCL algorithm controls diversity in deep ensembles.
problem Managing bias and variance in deep ensembles.
method Generalized bias-variance decomposition for arbitrary loss functions, leading to GNCL algorithm.
result Explicit control over ensemble diversity and smooth interpolation between independent and joint training.
A new method corrects weight values to improve treatment effect estimation.
problem Estimating heterogeneous treatment effects in high-dimensional data with sample selection bias.
method Differentiable Pareto-Smoothed Weighting (DPSW) framework.
result Our method outperforms existing methods in treatment effect estimation.
A new confidence measure improves self-training in biased data.
problem Improving self-training in biased data.
method Proposes a new confidence measure, T-similarity, based on ensemble diversity of linear classifiers.
result Empirically shows the benefit of T-similarity for pseudo-labeling policies on various datasets.
MGM improves media profiling by integrating textual and structural features.
problem Evaluating the bias and factuality of news media from digital data.
method MediaGraphMind (MGM) framework using variational EM, integrating textual and structural features.
result Achieves new state-of-the-art results in media profiling.
Investigates offline RL in factorisable action spaces, overcoming overestimation bias.
problem Overestimation bias in value estimates for unseen state-action pairs.
method Value-decomposition approach in DecQN, adapted for factorised discrete action spaces.
result Demonstrates the effectiveness of factorised approach in offline RL.
Feedback loops amplify dataset biases, affecting future model performance.
problem Feedback loops amplify biases in datasets, risking future model reliability.
method Formalized system where model interactions are recorded and reused, analyzed for bias amplification.
result Models that behave like samples from the training distribution are more stable and calibrated.
MANO normalizes logits to estimate test accuracy without labels.
problem Estimating test accuracy of OOD samples without labels.
method Applies Lp norm to normalized logits. result Achieves state-of-the-art performance across various architectures.
Benchmark assesses LLMs' causal inference skills, revealing significant limitations.
problem Lack of rigorous evaluation of LLMs' causal inference capabilities.
method CausalPitfalls benchmark with structured challenges and grading rubrics.
result Significant limitations in current LLMs' statistical causal inference.
Deep chest X-ray classifiers show bias in predicting diagnoses.
problem Bias in deep learning classifiers predicting diagnoses from chest X-rays.
method Trained convolutional neural networks on multiple public datasets to predict 14 diagnostic labels.
result True positive rates vary significantly among different protected attributes, indicating bias.
This paper addresses problematic global optima in VAEs, proposing a new inference method.
problem VAEs often yield solutions that violate modeling desiderata, leading to unrealistic data generation.
method The paper presents LiBI, a novel inference method to mitigate these issues.
result LiBI can learn better generative and inference models on synthetic datasets.
Modeling wildfire aerosols using satellite data to predict solar radiation reduction.
problem Accurately estimate and predict AOD propagation from wildfires using multi-source satellite data.
method Physics-informed statistical modeling integrating multi-source satellite data with an advection-diffusion equation.
result The proposed approach accurately predicts AOD propagation and demonstrates model interpretability.
Proposes a new semi-supervised learning method to reduce distribution mismatch.
problem Empirical distribution mismatch between labeled and unlabeled data in semi-supervised learning.
method Adversarial training and interpolation strategy to align labeled and unlabeled data distributions.
result Demonstrates improved performance on benchmark datasets SVHN and CIFAR10.
FairGP uses graph partitioning to make Graph Transformers fair and scalable.
problem Fairness issues in Graph Transformers, especially against sensitive features.
method Graph partitioning to minimize the influence of higher-order nodes and optimize attention mechanisms.
result FairGP improves fairness in Graph Transformers while reducing computational complexity.
Algorithm identifies and transfers unstable features to create robust classifiers.
problem Developing unbiased classifiers from input-label pairs alone.
method Contrast different data environments in source tasks to encode unstable features, then cluster target task data and minimize worst-case risk.
result Our method maintains robustness across synthetic and real-world environments.
Theoretical limits show experimental data can falsify but not validate causal estimates from observational studies.
problem Fundamental limits on validating causal estimates using experimental data in observational studies.
method Impossible inference framework, Gaussian Process based approach.
result Experimental data can falsify but not validate causal estimates from observational studies.
SOR-Mamba improves Mamba for robust time series forecasting by minimizing channel order bias.
problem Robust time series forecasting with Mamba's sequential order bias.
method SOR-Mamba incorporates regularization to minimize channel order discrepancy and introduces CCM for channel correlation preservation.
result SOR-Mamba enhances robustness to channel order and improves forecasting accuracy.
We tackle missing data in SBI methods and introduce a neural process approach.
problem Missing data in SBI methods can bias parameter estimation.
method We introduce a neural process approach to jointly learn imputation and inference.
result Our method provides robust inference outcomes compared to baselines.
Graph contrastive learning reveals unique inductive biases.
problem Understanding and optimizing graph contrastive learning methods.
method Systematic study of various GCL methods and their properties.
result GCL methods can work without positive or negative samples, and data augmentations have less impact.