Bayesian linear networks reveal optimal depth and width trade-offs.
problem Understanding how depth, width, and dataset size affect model quality in linear networks.
method Zero noise Bayesian inference with Gaussian weight priors and mean squared error.
result Optimal predictions at infinite depth and maximized Bayesian model evidence at infinite depth.
DORA analyzes deep neural networks' internal representations to detect spurious correlations.
problem Detecting spurious correlations in deep neural networks' internal representations.
method DORA uses Extreme-Activation (EA) distance measure to assess representation similarities.
result Identifies internal representations capable of detecting spurious correlations.
Our research proves neural collapse in deep ResNets and transformers is globally optimal.
problem Understanding neural collapse in deep learning models.
method Analysis of deep regularized transformers and ResNets trained with cross entropy or mean squared error loss.
result Global optima of deep regularized transformers and ResNets are approximately collapsed, becoming more prominent as depth increases.
New algorithm finds important synapses without training data.
problem Finding important synapses in neural networks without data.
method Iterative Synaptic Flow Pruning (SynFlow) based on conservation law.
result Algorithm consistently outperforms existing pruning methods.
New statistical guarantee improves conformal predictors for small datasets.
problem Uncertainty quantification for small datasets in surrogate models.
method Proposed a new statistical guarantee for conformal predictors, converging to standard CP for large datasets.
result The new guarantee offers relevant information about coverage for small data sizes, improving applicability.
This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In contrast to the existing approaches that seek regions bounded uniformly along all input features, we consider non-uniform bounds and use it to …
Paper uses news data to model asset correlations without market data.
problem Traditional risk models rely on market data; this paper offers an alternative.
method Uses encoder-only language models to embed news data, then calculates asset return distributions and covariance through Energy Distance.
result Established connections between distributional differences and excess returns co-movements using Energy Distance.
This work introduces a new method for coupling base and target densities in generative models.
problem Generating samples from complex target distributions using simple base distributions.
method Developed a framework of stochastic interpolants with data-dependent couplings.
result Constructing dynamical transport maps that serve as conditional generative models.
Measuring the similarity of two files is an important task in malware analysis, with fuzzy hash functions being a popular approach. Traditional fuzzy hash functions are data agnostic: they do not learn from a particular dataset how to determine similarity; their behavior is fixed across all datasets. In this paper, we …
Paper evaluates robustness of NAS against poisoning attacks.
problem Robustness of Neural Architecture Search (NAS) against poisoning attacks.
method Evaluation of Efficient NAS (ENAS) against carefully designed ineffective operations in poisoning attacks.
result Demonstrates how poisoning attacks exploit design flaws in ENAS controller.
TRAKNN detects rare atmospheric trajectories efficiently.
problem Detecting rare atmospheric anomalies over long periods.
method Unsupervised, recurrence-based kNN algorithm.
result Rare trajectories correspond to physical anomalies.
Linear regression is arguably the most prominent among statistical inference methods, popular both for its simplicity as well as its broad applicability. On par with data-intensive applications, the sheer size of linear regression problems creates an ever growing demand for quick and cost efficient solvers. Fortunately…
Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning research. In this paper, we replace the output activation function of DNNs, typically the data-agnostic softmax function, with a graph Laplacian-based high dimensional interpolati…
Study improves resilience against adversarial clean-label attacks in real and noisy settings.
problem Ensuring accurate predictions in the presence of adversarial clean-label samples.
method Sequential learning from a stream of i.i.d. data, allowing abstention for uncertain predictions.
result Theoretical analysis and adaptations for the agnostic setting with a clean-label adversary and noise.
New approach improves human activity recognition with wearables.
problem Improving human activity recognition with wearables.
method Exploiting latent relationships between multi-channel sensor modalities, data-agnostic augmentation, and a classification loss criterion.
result Achieves new state-of-the-art performance on four diverse activity recognition benchmarks.
Quantum circuit models learn better with specific initialization strategies.
problem Understanding and improving the optimization landscape of IQP-based generative models.
method Proved barren plateaus for random initialization, established lower bounds, and developed data-dependent initialization.
result Data-dependent initialization leads to faster convergence and better minimums.
Causal deep learning tackles causal inference using tensor factor analysis.
problem Addressing causal questions in data using neural networks.
method Tensor factor analysis and neural network architectures (causal capsules, tensor transformer, multilinear projection algorithm).
result Derives deep neural networks for causal inference with tensor factor analysis.
Wide neural networks with weight decay exhibit neural collapse.
problem Proving neural collapse in wide neural networks trained with weight decay.
method Generic guarantees on neural collapse for wide networks with weight decay, proving low training error and balancedness, and bounded conditioning.
result First proof of neural collapse in end-to-end training of wide neural networks with weight decay.
NTK-SAP improves neural network pruning by aligning training dynamics.
problem Improving neural network pruning to reduce training time and memory.
method Prune connections based on the spectrum of the Neural Tangent Kernel (NTK), using multiple random weight realizations and random inputs.
result Empirically, NTK-SAP achieves better performance than all baselines on multiple datasets.
Estimates KRR risk from training data for various kernels and hyperparameters.
problem Predicting the generalization error of Kernel Ridge Regression.
method Introduces SCT and KARE to approximate KRR risk from training data.
result KARE provides an excellent approximation of KRR risk and helps select good kernels.
MixKD improves large-scale language model compression and generalization.
problem Inefficient and resource-intensive large-scale language models.
method MixKD uses mixup data augmentation to enhance student model's generalization ability.
result MixKD leads to significant performance gains over standard KD and competitive baselines.
AGOP mechanism explains deep neural collapse in neural networks.
problem Explaining the rigid structure of data representations in deep neural networks.
method Introducing AGOP and Deep RFM to demonstrate DNC.
result AGOP mechanism causes deep neural collapse in neural networks.
LUNA improves linear attention for long sequences without sacrificing accuracy.
problem Quadratic computational cost of softmax attention in long-sequence domains.
method LUNA learns a learnable kernel feature map to reduce attention cost to linear while maintaining accuracy.
result LUNA achieves state-of-the-art performance on the LRA and excels at post-hoc conversion.
A new method normalizes flow mixtures for better inference across different data types.
problem Inference failure across diverse posterior geometries in normalizing flows.
method Introduces a two-stage framework with a stable global weighting mechanism based on sEMA.
result Achieves consistent NLL improvements and stable weight trajectories over baselines.
Proves local convergence of various online and recurrent optimization algorithms.
problem Proves local convergence of online and recurrent optimization algorithms not covered by standard stochastic gradient descent theory.
method Uses a general set of assumptions for learning dynamical systems online, adopting an 'ergodic' viewpoint.
result Local convergence results for online and recurrent optimization algorithms, including RMSProp, NoBackTrack, UORO, Adam, and RTRL.
This work improves SGD minibatch sampling using determinantal point processes based on orthogonal polynomials.
problem Improving variance reduction in stochastic gradient descent (SGD) for large datasets.
method Orthogonal polynomial-based determinantal point processes for sampling minibatches in SGD.
result DPP minibatches lead to a smaller mean square approximation error than uniform minibatches.