Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce mi…
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “loss visualization”
Paper proposes a new black-box attack approach to minimize visual distortion.
problem Constructing adversarial examples that minimize visual distortion in a black-box threat model.
method Learning the noise distribution of adversarial examples to approximate the gradient of a non-differentiable loss function.
result The proposed attack results in much lower visual distortion compared to state-of-the-art black-box attacks.
Visualizing the Loss Landscape of Actor Critic Methods with Applications in Inventory Optimizationcs.LG
Study visualizes actor-critic loss landscapes for inventory optimization.
problem Difficulties in solving multi-store dynamic inventory control problems.
method Low-dimensional visualizations of actor loss function.
result Loss landscapes favor optimal policies in reinforcement learning.
Spectral images captured by satellites and radio-telescopes are analyzed to obtain information about geological compositions distributions, distant asters as well as undersea terrain. Spectral images usually contain tens to hundreds of continuous narrow spectral bands and are widely used in various fields. But the vast…
A framework visualizes embedding spaces of neural survival analysis models using anchor directions.
problem Visualizing complex embeddings in neural survival analysis models.
method Estimating anchor directions through clustering or user-supplied concepts, revealing relationships with raw inputs and survival times.
result Visualization strategies reveal how anchor directions relate to raw clinical features and survival time distributions.
Researchers improve visualization of neural network loss landscapes.
problem Understanding neural network generalization performance.
method Novel 'jump and retrain' procedure, non-linear dimensionality reduction (PHATE), computational homology.
result Improved visualization and quantification of neural network generalization performance.
t-SNE loses important features in data visualization.
problem t-SNE's loss of important features in data visualization.
method Established mathematical framework to understand t-SNE's loss in different scenarios.
result t-SNE loses important features of data in various scenarios.
This work uses visualizations to make generalization of neural networks more intuitive.
problem Understanding the reasons behind neural networks' ability to generalize to unseen data.
method Visualization methods to explain the geometry of loss landscapes and the role of dimensionality in optimization.
result Visualization helps in understanding how optimizers settle into minima that generalize well.
A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and whether a concise view of the interactions between a hardened decision map and input samples is possible. We first provide a means of visually co…
New findings suggest adversarial training does not flatten loss landscapes, challenging current intuition.
problem Understanding and improving generalization in deep learning.
method Loss surface visualization with filter normalization technique.
result Adversarial training does not result in flatter loss landscapes, challenging current intuition.
Method generates visual explanations for similarity models without classification.
problem Lack of visual explanations for similarity models trained without classification loss.
method Gradient-based visual attention using learned feature embeddings.
result Attention maps improve model performance and can be used as constraints.
Introduces CHL, a new loss function for continuous similarity learning.
problem Binary similarity learning limitations.
method CHL is a novel loss function that generalizes histogram loss to continuous similarities.
result CHL solves a wider range of tasks including similarity learning, representation learning, and data visualization.
Improved zero-shot learning with graph-based regularization.
problem Transfer knowledge to unknown classes in zero-shot learning.
method Isoperimetric loss for learning map between visual and semantic embeddings, exploiting graph structure.
result Regularization alone outperforms state-of-the-art methods in zero-shot learning benchmarks.
Study improves recognition of long-tail visual relationships.
problem Improving recognition of structured visual relationships from long-tail classes.
method Developed two benchmarks, introduced VilHub loss, and applied RelMix augmentation.
result Simple techniques significantly improved performance on tail classes.
GraphTSNE visualizes graph data by integrating graph structure and node features.
problem Lack of suitable visualization techniques for graph-structured data.
method GraphTSNE combines t-SNE with graph convolutional networks to visualize graph data.
result GraphTSNE produces better visualizations of graph data compared to existing methods.
GradVis visualizes and analyzes deep neural network optimization surfaces efficiently.
problem Understanding and optimizing deep neural network training landscapes.
method Developed an open-source library GradVis for efficient visualization and analysis of optimization surfaces.
result GradVis enables plotting of optimization surfaces and trajectories for large networks.
Study evaluates interpretability of time series foundation models' latent spaces.
problem Improving interpretability of latent spaces in time series models for visual analytics.
method Evaluated MOMENT family of transformer-based models on five datasets, fine-tuning for performance.
result Fine-tuning improved latent space clarity but limited interpretability remained.
This research evaluates neural network robustness through loss visualization and a new metric.
problem Neural networks' robustness property is insufficiently investigated compared to adversarial attacks and defenses.
method Loss visualization and a new robustness metric to evaluate model stability.
result The proposed robustness metric provides a more reliable evaluation of model stability, uniformed across different models and settings.
New method prevents class collapse in metric learning with margin-based losses.
problem Class collapse in metric learning due to diverse intra-class samples.
method Proposed a sampling method to select nearest same-class samples as positive elements in tuple.
result Demonstrated clear benefits on various fine-grained image retrieval datasets.
Boosts neural network performance by improving weight separability.
problem Improving the separability of weight vectors in neural networks.
method Proposes a new evaluation metric and feed-backward reconstruction loss to encourage weight separability.
result Improves visual recognition performance across various tasks.
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable t…
Prototype-based memory network learns visual categories from unlabeled data.
problem Learning from nonstationary, unlabeled data with sequential dependencies.
method Online prototype-based memory network with contrastive loss.
result Significantly better category recognition compared to state-of-the-art methods.
DEN creates interpretable visualizations using Siamese networks.
problem Creating interpretable visualizations of complex datasets.
method Differentiating Embedding Networks (DEN) using Siamese neural networks and loss functions.
result DEN outperforms existing techniques on FashionMNIST and interpretable features are identified.
AVH scores measure sample hardness, improving model calibration.
problem CNNs' poor calibration and overconfidence issues.
method AVH score based on normalized angular distance between feature embeddings and target classifiers.
result AVH scores correlate with human visual hardness and improve model calibration.
BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.
problem Exploration in visually complex environments.
method Optimizes a single prediction loss in latent space to learn world representation, dynamics, and exploration policy.
result Achieves superhuman performance on Atari games with simpler design.
UMAP's true loss function differs from what was previously thought, focusing on nearest neighbor graph similarities.
problem Understanding the true effectiveness and mechanism of UMAP for high-dimensional data visualization.
method Deriving UMAP's effective loss function in closed form and analyzing its optimization scheme.
result UMAP aims to reproduce similarities encoded in the nearest neighbor graph, not the full high-dimensional similarities.
The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to r…
M-PHATE visualizes neural network learning dynamics.
problem Understanding neural network performance and learning dynamics.
method Multislice PHATE (M-PHATE) for visualizing neural network hidden representations.
result M-PHATE provides detailed summaries of learning dynamics without needing validation data.
Paper introduces Balanced Meta-Softmax for better long-tailed visual recognition.
problem Long-tailed distribution mismatch between training and testing data.
method Balanced Meta-Softmax, an unbiased extension of Softmax, using a Meta Sampler.
result Balanced Meta-Softmax outperforms state-of-the-art solutions on visual recognition and instance segmentation.
New visualization techniques reveal GAN optimization landscapes.
problem Challenges in training GANs compared to standard deep neural networks.
method Visualization techniques for optimization landscapes of GANs.
result GANs converge to saddle points, not minima, achieving excellent performance.
Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performanc…
A novel supervised visualization technique for data exploration.
problem Lack of supervised dimensionality reduction methods considering class labels.
method Random forest proximities and diffusion-based dimensionality reduction.
result Retains local and global structures in data, emphasizing important variables.
SuNCEt accelerates contrastive learning with minimal labeled data.
problem Efficiently learning visual representations with limited labeled data.
method Noise-contrastive estimation and neighbourhood component analysis-based semi-supervised loss.
result SuNCEt achieves semi-supervised learning accuracy with less than half the labeled data.
The paper analyzes how speech enhancement and recognition can be improved in noisy environments.
problem Improving speech recognition in multi-talker scenarios with limited resources.
method Developed and trained two LSTM-based models for speech enhancement and phone recognition, then studied their joint optimization.
result Joint optimization of speech enhancement and recognition leads to a significant reduction in Phone Error Rate (PER).
New method evaluates visual explanations of deep models using adversarial perturbations.
problem Lack of objective evaluation of visual explanations of deep models.
method Proposes an adversarial perturbation approach to evaluate visual explanations of deep models.
result Demonstrates the effectiveness of the proposed approach through comparisons with existing methods.
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a gene…
Reviews recent findings on neural network landscapes.
problem Non-convexity of loss functions causing bad landscapes.
method Rigorous geometric analysis and empirical exploration.
result Wide neural nets may have sub-optimal local minima.
This study addresses the challenges of dynamic mini-batch sub-sampling in neural network training.
problem Challenges in training neural networks due to dynamic mini-batch sub-sampling.
method Distinguishes between static and dynamic sub-sampling, recasting optimization to find SNN-GPPs.
result SNN-GPPs are less susceptible to sub-sampling-induced discontinuities and better approximate true optima.
Large learning rates improve neural network generalization, study shows.
problem Understanding why large learning rates lead to better neural network generalization.
method Visual analysis of training and testing loss landscapes, introduction of a nonlinear model.
result Extended phase with large learning rates leads to near-optimal generalization.
Introduces bi-temperature logistic loss for more robust training.
problem Training neural nets with noise robustness.
method Introduces two temperatures into logistic loss and Bregman divergences.
result Training becomes more robust to noise with bi-temperature loss.
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found i…
Paper proposes self-supervised method for accurate speaker diarization.
problem Speaker diarization without massive labeling effort.
method Introduces dynamic triplet loss and multinomial loss for audio-video synchronization.
result Best model yields +8% F1-score improvement and diarization error rate reduction.
Recent advances in conditional image generation tasks, such as image-to-image translation and image inpainting, are largely accounted to the success of conditional GAN models, which are often optimized by the joint use of the GAN loss with the reconstruction loss. However, we reveal that this training recipe shared by …
A simple framework improves visual representation learning.
problem Efficiently learning useful visual representations from unlabeled data.
method Contrastive learning with simplified framework and systematic study of components.
result Significant improvement in accuracy compared to previous methods.
Predicting Glaucoma Visual Field Loss by Hierarchically Aggregating Clustering-based Predictorsstat.ML
This study addresses the issue of predicting the glaucomatous visual field loss from patient disease datasets. Our goal is to accurately predict the progress of the disease in individual patients. As very few measurements are available for each patient, it is difficult to produce good predictors for individuals. A rece…
GCML preserves geometric structure in manifold clustering for diverse data types.
problem Loss functions in manifold clustering can corrupt latent space structure.
method GCML framework with isometric and ranking losses for geometric structure preservation.
result GCML outperforms other methods in latent space structure preservation and performance metrics.
In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network. Our model consists of a top-down stack of GANs, each learned to generate lower-level representations conditioned on …
Visually predicting the stability of block towers is a popular task in the domain of intuitive physics. While previous work focusses on prediction accuracy, a one-dimensional performance measure, we provide a broader analysis of the learned physical understanding of the final model and how the learning process can be g…