goldblum / TruthOrBackpropaganda
An empirical investigation of deep learning theory
☆16Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for TruthOrBackpropaganda
- Code for Unbiased Implicit Variational Inference (UIVI)☆13Updated 5 years ago
- A fast and efficient way to compute a differentiable bound on the singular values of convolution layers☆11Updated 5 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated last year
- Code for "Exponential Family Estimation via Adversarial Dynamics Embedding" (NeurIPS 2019)☆13Updated 4 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- ☆19Updated 4 years ago
- ☆55Updated 4 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- ☆36Updated 2 years ago
- ☆35Updated last year
- ☆37Updated 3 years ago
- Geometric Certifications of Neural Nets☆41Updated 2 years ago
- MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".☆18Updated last year
- Distilling Model Failures as Directions in Latent Space☆45Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆53Updated last year
- ☆31Updated 4 years ago
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆17Updated 2 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- ☆17Updated 2 years ago
- Code accompanying VarGrad: A Low-Variance Gradient Estimator for Variational Inference☆12Updated 4 years ago
- Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited☆36Updated last year
- ☆25Updated 4 years ago
- A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturb…☆11Updated 4 years ago
- Implementation of Information Dropout☆39Updated 7 years ago
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- SGD and Ordered SGD codes for deep learning, SVM, and logistic regression☆34Updated 4 years ago
- Implicit generative models and related stuff based on the MMD, in PyTorch☆16Updated 4 years ago