Understanding Adam Requires Better Rotation Dependent Assumptions

Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This paper investigates Adam's sensitivity to rotations of the parameter space. We demonstrate that Adam's performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice of basis. This reveals that conventional rotation-invariant assumptions are insufficient to capture Adam's advantages theoretically. To better understand the rotation-dependent properties that benefit Adam, we also identify structured rotations that preserve or even enhance its empirical performance. We then examine the rotation-dependent assumptions in the literature, evaluating their adequacy in explaining Adam's behavior across various rotation types. This work highlights the need for new, rotation-dependent theoretical frameworks to fully understand Adam's empirical success in modern machine learning tasks.

Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching

Privacy and regulatory constraints make data generation vital to advancing machine learning without relying on real-world datasets. A leading approach for tabular data generation is the Forest Flow (FF) method, which combines Flow Matching with XGBoost. Despite its good performance, FF is slow and makes errors when treating categorical variables as one-hot continuous features. It is also highly sensitive to small changes in the initial conditions of the ordinary differential equation (ODE). To overcome these limitations, we develop Heterogeneous Sequential Feature Forest Flow (HS3F). Our method generates data sequentially (feature-by-feature), reducing the dependency on noisy initial conditions through the additional information from previously generated features. Furthermore, it generates categorical variables using multinomial sampling (from an XGBoost classifier) instead of flow matching, improving generation speed. We also use a Runge-Kutta 4th order (Rg4) ODE solver for improved performance over the Euler solver used in FF. Our experiments with 25 datasets reveal that HS3F produces higher quality and more diverse synthetic data than FF, especially for categorical variables. It also generates data 21-27 times faster for datasets with $\geq20%$ categorical variables. HS3F further demonstrates enhanced robustness to affine transformation in flow ODE initial conditions compared to FF. This study not only validates the HS3F but also unveils promising new strategies to advance generative models.

Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality

The Fr\'echet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectiveness relies on critical assumptions. Our analysis reveals three significant limitations: (1) the non-Gaussianity of the Inflated 3D Convnet (I3D) feature space; (2) the insensitivity of I3D features to temporal distortions; (3) the impractical sample sizes required for reliable estimation. These findings undermine FVD's reliability and show that FVD falls short as a standalone metric for video generation evaluation. After extensive analysis of a wide range of metrics and backbone architectures, we propose JEDi, the JEPA Embedding Distance, based on features derived from a Joint Embedding Predictive Architecture, measured using Maximum Mean Discrepancy with polynomial kernel. Our experiments on multiple open-source datasets show clear evidence that it is a superior alternative to the widely used FVD metric, requiring only 16% of the samples to reach its steady value, while increasing alignment with human evaluation by 34%, on average.

Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Trees

Generating novel molecules is challenging, with most representations leading to generative models producing many invalid molecules. Spanning Tree-based Graph Generation (STGG) is a promising approach to ensure the generation of valid molecules, outperforming state-of-the-art SMILES and graph diffusion models for unconditional generation. In the real world, we want to be able to generate molecules conditional on one or multiple desired properties rather than unconditionally. Thus, in this work, we extend STGG to multi-property-conditional generation. Our approach, STGG+, incorporates a modern Transformer architecture, random masking of properties during training (enabling conditioning on any subset of properties and classifier-free guidance), an auxiliary property-prediction loss (allowing the model to self-criticize molecules and select the best ones), and other improvements. We show that STGG+ achieves state-of-the-art performance on in-distribution and out-of-distribution conditional generation, and reward maximization.

Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion

With recent advances in video prediction, controllable video generation has been attracting more attention. Generating high fidelity videos according to simple and flexible conditioning is of particular interest. To this end, we propose a controllable video generation model using pixel level renderings of 2D or 3D bounding boxes as conditioning. In addition, we also create a bounding box predictor that, given the initial and ending frames' bounding boxes, can predict up to 15 bounding boxes per frame for all the frames in a 25-frame clip. We perform experiments across 3 well-known AV video datasets: KITTI, Virtual-KITTI 2 and BDD100k.

LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters

A good initialization of deep learning models is essential since it can help them converge better and faster. However, pretraining large models is unaffordable for many researchers, which makes a desired prediction for initial parameters more necessary nowadays. Graph HyperNetworks (GHNs), one approach to predicting model parameters, have recently shown strong performance in initializing large vision models. Unfortunately, predicting parameters of very wide networks relies on copying small chunks of parameters multiple times and requires an extremely large number of parameters to support full prediction, which greatly hinders its adoption in practice. To address this limitation, we propose LoGAH (Low-rank GrAph Hypernetworks), a GHN with a low-rank parameter decoder that expands to significantly wider networks without requiring as excessive increase of parameters as in previous attempts. LoGAH allows us to predict the parameters of 774-million large neural networks in a memory-efficient manner. We show that vision and language models (i.e., ViT and GPT-2) initialized with LoGAH achieve better performance than those initialized randomly or using existing hypernetworks. Furthermore, we show promising transfer learning results w.r.t. training LoGAH on small datasets and using the predicted parameters to initialize for larger tasks. We provide the codes in https://github.com/Blackzxy/LoGAH .

Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees

Tabular data is hard to acquire and is subject to missing values. This paper proposes a novel approach to generate and impute mixed-type (continuous and categorical) tabular data using score-based diffusion and conditional flow matching. Contrary to previous work that relies on neural networks as function approximators, we instead utilize XGBoost, a popular Gradient-Boosted Tree (GBT) method. In addition to being elegant, we empirically show on various datasets that our method i) generates highly realistic synthetic data when the training dataset is either clean or tainted by missing data and ii) generates diverse plausible data imputations. Our method often outperforms deep-learning generation methods and can trained in parallel using CPUs without the need for a GPU. To make it easily accessible, we release our code through a Python library on PyPI and an R package on CRAN.

Diffusion models with location-scale noise

Diffusion Models (DMs) are powerful generative models that add Gaussian noise to the data and learn to remove it. We wanted to determine which noise distribution (Gaussian or non-Gaussian) led to better generated data in DMs. Since DMs do not work by design with non-Gaussian noise, we built a framework that allows reversing a diffusion process with non-Gaussian location-scale noise. We use that framework to show that the Gaussian distribution performs the best over a wide range of other distributions (Laplace, Uniform, t, Generalized-Gaussian).

PopulAtion Parameter Averaging (PAPA)

Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs at inference time. To avoid these costs, multiple neural networks can be combined into one by averaging their weights (model soups). However, this usually performs significantly worse than ensembling. Weight averaging is only beneficial when weights are similar enough (in weight or feature space) to average well but different enough to benefit from combining them. Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging. PAPA leverages a population of diverse models (trained on different data orders, augmentations, and regularizations) while occasionally (not too often, not too rarely) replacing the weights of the networks with the population average of the weights. PAPA reduces the performance gap between averaging and ensembling, increasing the average accuracy of a population of models by up to 1.1% on CIFAR-10, 2.4% on CIFAR-100, and 1.9% on ImageNet when compared to training independent (non-averaged) models.

CNT : A new Algorithm for Leveraging Top-Down Feedback

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in classification) at a random noise level (from small to large noise). At inference time, since we do not know the target, we run the network with only noise in place of the noisy target. CNT provides hints through the noisy label (with less noise, we can more easily infer the true target). This give two main benefits: 1) the top-down feedback allows the model to focus on simpler and more digestible sub-problems and 2) rather than learning to solve the task from scratch, the model will first learn to master easy examples (with less noise), while slowly progressing toward harder examples (with more noise).