Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

88176264352 · Jun 202019922001200920182026
48 results for adaptive encoders

SplitWise enhances stepwise regression by adaptively encoding numeric predictors into binary features.

problem Capturing nonlinear relationships in regression models without sacrificing interpretability.
method Adaptive encoding of numeric predictors into binary features using shallow decision trees, assessed by AIC or BIC.
result Consistently produces more parsimonious and generalizable models than traditional techniques.

Adaptive Quantization Modules enable online continual compression of non-i.i.d data streams.

problem Learning to compress and store a dataset from a non-i.i.d data stream, only observing each sample once.
method Discrete auto-encoders and Adaptive Quantization Modules (AQM) to control compression ability.
result Significant gains on continual learning benchmarks with AQM replacing episodic memory.

Transformer adapts to graphs with adaptive attention and auto-regressive decoding.

problem Transformers struggle with graph data due to non-sequential nature.
method Proposes GRAT, a Transformer variant with adaptive attention and auto-regressive decoding.
result GRAT achieves state-of-the-art performance on molecule property predictions and generation tasks.

Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.

problem Improving active noise control with neural adaptive filters.
method Training an auto-encoder on filter coefficients, constraining weights to latent variables, and updating in latent space.
result Latent FxLMS converges in fewer steps with comparable error to standard FxLMS.

Framework adds invariance to pretrained networks without fine-tuning.

problem Adding invariance to pretrained networks without altering original behavior.
method Post-training augmentation invariance framework with Markov-Wasserstein minimization and Wasserstein correlation maximization losses.
result Adapter networks improve classification accuracy on rotated and noisy images.

A new image interpolation model using sparse representation and nonlocal linear regression.

problem Image interpolation without blurring and noise.
method Sparse representation, nonlocal self-similarity, nonlocal linear regression, adaptive sub-dictionary learning, weighted encoding.
result Our method outperforms state-of-the-art methods in quantitative measures and visual quality.

FAWMF adapts weights for implicit feedback recommendation efficiently.

problem Challenges in treating unobserved data as negative in implicit feedback recommendation.
method FAWMF uses a variational auto-encoder with a parameterized neural network to adaptively assign personalized data confidence weights, and fBGD for efficient learning.
result FAWMF and fBGD outperform existing methods in real-world datasets.

Adaptive framework for learning latent space dimensions in GANs.

problem Inadequate latent space dimensions lead to poor generative models for complex data.
method Proposes a novel framework (LWGAN) that adaptively learns latent dimensions of data manifolds.
result Proves that the estimated intrinsic dimension is a consistent estimate of the true data manifold dimension.

Adaptive ML learns complex time-varying systems without new data.

problem Applying ML to time-varying systems with shifting distributions.
method Mapping high-dimensional inputs to low-dimensional latent space, actively tuning latent space based on feedback.
result Learning correlations and tracking system evolution in real-time without new data.

Deep learning approach for efficient IoT task scheduling in MEC networks.

problem Minimizing task latency in IoT users with large-scale MEC systems.
method Stacked auto-encoder for data compression, adaptive simulated annealing, experience replay.
result Near-optimal performance with significantly reduced computational time.

Few-shot domain adaptation improves autoencoder performance in changing wireless channels.

problem Frequent retraining of autoencoder for low decoding error rate in changing channel conditions is impractical.
method Uses Gaussian mixture density network and class and component-conditional affine transformations for few-shot adaptation.
result Effective adaptation using very small number of target domain samples, improving performance in real mmWave setups.

A new graph generation model uses Mallat's scattering transform.

problem Unclear mathematical properties and difficulty in training good generative models for graphs.
method Proposes a graph generation model using a Gaussianized graph scattering transform.
result Demonstrates state-of-the-art performance in link prediction and graph/signal generation.

AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.

problem Challenges in attributed graph embedding, especially in preserving optimal low-pass characteristics and robustness.
method AGE, a novel framework combining Laplacian smoothing and adaptive encoding, addresses these issues.
result AGE consistently outperforms state-of-the-art methods on node clustering and link prediction tasks.

A novel feedbackward approach for semantic segmentation reduces parameter count.

problem Semantic segmentation challenges in terms of model complexity and performance.
method Reverse-direction encoder-decoder architecture using the same network for both encoding and decoding.
result Significantly outperforms other models using only 13 VGG-16 layers, achieving higher IoU scores.

End-to-end meta-learned system for image compression.

problem Reducing the gap between training and inference conditions in image compression.
method Model-Agnostic Meta-learning approach for latent tensor overfitting and updating encoder and decoder networks.
result Meta-learned system achieves better compression performance compared to traditional methods.

WeatherFormer learns robust weather features from small datasets.

problem Modeling complex weather dynamics from limited data.
method Pretrained transformer encoder on large satellite dataset, with spatiotemporal encoding.
result State-of-the-art performance in county-level soybean yield prediction and influenza forecasting.

DMGNN predicts 3D human motions using adaptive multiscale graphs.

problem Predicting 3D skeleton-based human motions accurately.
method Dynamic multiscale graph neural networks (DMGNN) with adaptive multiscale graphs and MGCU.
result DMGNN outperforms state-of-the-art methods in short and long-term predictions.

SAHMM-VAE separates sources adaptively using hidden Markov priors.

problem Unsupervised blind source separation.
method Source-wise adaptive Hidden Markov prior variational autoencoder.
result Different latent dimensions align with different source-specific temporal organizations.

New techniques improve channel prediction in noisy wireless systems.

problem Predicting channels in wireless communication systems from noisy observations.
method Adapted sequence-to-sequence models and transformers with reverse positional encoding and reversed encoder outputs.
result Improved robustness and relationship capture in channel prediction models.

Deep neural networks solve Raven's Progressive Matrices with high accuracy.

problem Testing relational reasoning in machine learning systems.
method Combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding.
result Deep neural networks achieve 98.0 percent accuracy, significantly improving over previous methods.

MAES architecture improves working memory task performance through multi-task and transfer learning.

problem Improving performance on complex working memory tasks.
method Memory-Augmented Encoder-Solver (MAES) architecture with dual recurrent neural network controllers and a shared memory module.
result MAES models achieve task-size generalization, handling inputs 50 times longer than training data.

Unified MTL framework for heterogeneous data integrates shared and task-specific encoders.

problem Efficiently sharing information across multiple tasks with heterogeneous data.
method Dual-encoder framework with task-shared and task-specific encoders.
result Unified algorithm alternates learning task-specific and shared encoders and coefficients.

We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportion…

2016-11-18abs ↗pdf ↗

We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in st…

2017-05-29abs ↗pdf ↗

New approach improves domain adaptation by relaxing distribution alignment constraints.

problem Improving domain adaptation when target distribution differs from source distribution.
method Asymmetrically-relaxed distribution alignment to minimize target error under varying conditions.
result Empirical and theoretical benefits demonstrated on synthetic and real datasets.

Improved model predicts interactions in complex systems better than previous methods.

problem Predicting interactions in complex systems like social networks or physical dynamics.
method Factorized Neural Relational Inference (fNRI) model that separates interactions into layers.
result fNRI significantly outperforms original NRI in edge and trajectory prediction.