New algorithm for weighted low rank approximation with provable guarantees.
problem Weighted low rank approximation (WLRA) is computationally hard.
method Reweights the low rank solution using the weight matrix itself.
result Provably optimal approximation guarantees for WLRA.
Weight Decay induces low-rank weight matrices in neural networks, improving generalization.
problem Improving generalization in neural networks.
method Training ReLU NN with Weight Decay and Stochastic Gradient Descent.
result The weight matrix of a trained NN is approximately rank-two.
New bound for neural networks with full-rank weights, independent of network width.
problem Understanding generalization of neural networks with full-rank weight matrices.
method Using Koopman operators to derive a tighter generalization bound for full-rank weight matrices.
result The bound is tighter than existing norm-based bounds when condition numbers are small.
New method corrects quantization errors in LLMs using low-rank matrices.
problem Correcting quantization errors in large language models.
method Introducing low-rank weight matrices to correct quantized activations in LLMs.
result Reduces accuracy gap with original model by more than 50% using low-rank matrices.
Algorithm ranks assets in fluctuating markets.
problem Ranking assets in nonstationary time series.
method Naive Bayes asset ranker that adjusts weights based on performance.
result Outperforms traditional methods and S&P 500 index.
SGD and weight decay encourage neural networks to learn low-rank weight matrices.
problem The bias of SGD towards low-rank weight matrices in neural networks.
method The study investigates the effect of SGD and weight decay on the rank of weight matrices in neural networks, both theoretically and empirically.
result Training with SGD and weight decay induces a bias towards rank minimization in weight matrices, which becomes more pronounced with smaller batch sizes and stronger weight decay.
We present a method of rank-optimal weighting which can be used to explore the best possible position of a subject in a ranking based on a composite indicator by means of a mathematical optimization problem. As an example, we explore the dataset of the OECD Better Life Index and compute for each country a weight vector…
Paper develops a new weighted low-rank matrix approximation technique.
problem Matrix completion with missing data.
method Element-wise weighted generalization of low-rank matrix approximation.
result Proposes an algorithm and acceleration techniques for solving the weighted problem.
LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.
problem Efficient processing of low-rank weight decompositions in large finetuned models.
method Developed symmetry-aware invariant and equivariant LoL models to process LoRA weights.
result LoL models can predict CLIP scores, finetuning data attributes, and accuracy on downstream tasks.
We propose a new learning to rank algorithm, named Weighted Margin-Rank Batch loss (WMRB), to extend the popular Weighted Approximate-Rank Pairwise loss (WARP). WMRB uses a new rank estimator and an efficient batch training algorithm. The approach allows more accurate item rank approximation and explicit utilization of…
Paper discusses extending Gini score for tied rankings and case weights.
problem Extending Gini score for tied rankings and case weights.
method Discuss and adapt Gini score for ties and case weights.
result Gini score can be used for tied rankings and case weights.
The paper connects neural collapse and low-rank bias in networks with L2 regularization.
problem Understanding the emergence of low-rank bias and neural collapse in L2-regularized networks.
method Unified theoretical framework linking TCV and rank of weight matrices, proving global optimality of DNC1, and establishing a benign landscape property.
result Zero TCV across intermediate layers minimizes representation cost under natural architectural constraints, and DNC1 is globally optimal.
Standardizes weighted ranking correlation coefficients to maintain zero expected value.
problem Measuring correlation between weighted rankings of items.
method Develops a standardization function g(·) that transforms coefficients to zero expected value under randomness.
result A general standardization function g(Γ) that preserves the domain [-1,1] and reduces to the identity for coefficients already satisfying zero-expected-value property.
Low-rank structure emerges in neural networks during learning.
problem Understanding the evolution of synaptic connectivity over learning.
method Investigated the rank of 3-tensor formed by weight matrices throughout learning.
result Inferred weights are low-tensor-rank and evolve in a fixed low-dimensional subspace.
The paper reveals low-rank structure in neural network gradients, influenced by data and model parameters.
problem Investigating low-rank structure in gradients of neural networks under relaxed assumptions.
method Spiked data model, relaxation of isotropy assumptions, analysis of mean-field and neural-tangent-kernel scalings.
result Gradient of input weights is approximately low rank, dominated by two rank-one terms.
Proposes a new method for rank-consistent ordinal regression without weight-sharing constraints.
problem Ordinal response variables in real-world prediction problems are often ignored by conventional classification losses.
method CORN framework using conditional training sets and the chain rule for conditional probability distributions.
result Improves performance substantially compared to the CORAL reference approach without weight-sharing restrictions.
Study of g-vector cones in cluster algebras from weighted orbifolds.
problem Determine the closure of g-vector cones in cluster algebras. method Analyzing g-vector cones in a cluster algebra defined from a weighted orbifold. result Closure of the union of g-vector cones is Rn except for specific weighted orbifolds. LoRA fine-tuning explained with gradient dynamics for low-rank perturbations.
problem Understanding why gradient descent converges to useful low-rank perturbations in LoRA fine-tuning.
method Generalized student-teacher setting with i.i.d. samples and online gradient descent.
result Gradient descent converges to the teacher model in dkO(1) iterations under certain conditions. Many applications require recovering a ground truth low-rank matrix from noisy observations of the entries, which in practice is typically formulated as a weighted low-rank approximation problem and solved by non-convex optimization heuristics such as alternating minimization. In this paper, we provide provable recover…
Weighted log-rank tests are arguably the most widely used tests by practitioners for the two-sample problem in the context of right-censored data. Many approaches have been considered to make weighted log-rank tests more robust against a broader family of alternatives, among them, considering linear combinations of wei…
New algorithm improves deep learning models' robustness without sacrificing accuracy.
problem Low-rank methods compromise model robustness against adversarial perturbations.
method Robust low-rank training via approximate orthonormal constraints.
result Ensures well-conditioning and better adversarial robustness without sacrificing model accuracy.
Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.
problem Sequential budget allocation in ranking and selection
method Annealed weighted soft-min framework
result Surrogate converges uniformly to the hard minimum, soft-min weights concentrate on active challengers, and target allocation map is continuous.
Introduces nondecreasing rank for matrices and tensors, developing methods and applications.
problem Finding low-rank approximations for matrices and tensors with monotonic constraints.
method Developed a variant of hierarchical alternating least squares algorithm for finding low ND rank approximations.
result Low ND rank factorizations can be found and interpreted for real-world datasets.
Stochastic gradient descent on manifolds improves low-rank approximation.
problem Efficiently approximate large matrices with lower rank.
method Stochastic gradient descent on a manifold.
result Algorithm outperforms Euclidean space methods on Netflix Prize data.
Proposes a new sampling policy for ranking and selection problems.
problem Improving ranking and selection in adaptive sampling policies.
method Annealed entropic allocation, using soft-min weights and saddlepoint corrections.
result Consistently competitive performance in various settings.
Ranking is a key aspect of many applications, such as information retrieval, question answering, ad placement and recommender systems. Learning to rank has the goal of estimating a ranking model automatically from training data. In practical settings, the task often reduces to estimating a rank functional of an object …
LR-EDNN reduces PDE solver complexity by limiting network weights to low-rank subspace.
problem Efficiently solving time-dependent PDEs with deep neural networks.
method Low-rank constraint on network weights using SVD for efficient parameter updates.
result LR-EDNN achieves comparable accuracy to full EDNN with fewer parameters and lower cost.
Recently, there has been an abundance of works on designing Deep Neural Networks (DNNs) that are robust to adversarial examples. In particular, a central question is which features of DNNs influence adversarial robustness and, therefore, can be to used to design robust DNNs. In this work, this problem is studied throug…
Random weights in GNNs match learned weights in performance.
problem Feature rank collapse in GNNs.
method Replacing learned weights with random weights.
result Random weights achieve comparable performance to learned weights, reducing training time and memory usage.
Deep ResNets favor low bottleneck rank with proper hyperparameters.
problem Understanding the inductive bias of deep neural networks.
method Computed minimum-norm weights of a deep linear ResNet.
result Deep nonlinear ResNets have an inductive bias towards minimizing bottleneck rank.
Study evaluates thresholds for removing noise from DNN weights using random matrix theory.
problem Removing noise from deep neural network weights for better approximation.
method Model weights as signal + noise, use random matrix theory to estimate thresholds, evaluate using cosine similarity.
result Proposed threshold estimation method improves approximation quality.
Investigates portfolio selection for rank-dependent utilities in incomplete markets.
problem Portfolio selection for agents with rank-dependent utility in incomplete financial markets.
method Characterizes deterministic strict equilibrium strategies for constant-coefficient and time-invariant probability weighting functions. Addresses the issue of selecting an optimal strategy from multiple equilibrium strategies for time-variant probability weighting functions.
result Characterizes deterministic strict equilibrium strategies and identifies optimal strategies from multiple equilibrium strategies.
Suppose that X1,…,Xn are continuous semimartingales that are reversible and have nondegenerate crossings. Then the corresponding rank processes can be represented by generalized Stratonovich integrals, and this representation can be used to decompose the relative log-return of portfolios generated by functi…
Predicting neural network accuracy from weights without testing.
problem Predicting neural network performance based on weights alone.
method Used simple statistics of weights to rank neural networks' performance.
result Simple predictors can rank networks' performance with high accuracy (R2 score > 0.98).
For a 2-periodic link L~ in the thickened annulus and its quotient link L, we exhibit a spectral sequence with E1≅AKh(L~)⊗F2F2[θ,θ−1]⇉E∞≅AKh(L)⊗F2F2[θ,θ−1]. This spectral sequence splits along qu…
Recently, Factorization Machines (FM) has become more and more popular for recommendation systems, due to its effectiveness in finding informative interactions between features. Usually, the weights for the interactions is learnt as a low rank weight matrix, which is formulated as an inner product of two low rank matri…
Bayesian neural networks can be simplified by parameterizing weights as rank-r matrices, reducing parameter count and improving performance.
problem High parameter count in standard Bayesian neural networks.
method Parameterize weights as W=ABop with A∈Rmimesr, B∈Rnimesr, inducing a singular posterior. result PAC-Bayes generalization bounds and loss bounds show improved performance with fewer parameters.
Paper tackles ranking items with a semi-random comparison graph and a monotone adversary.
problem Ranking items based on pairwise comparisons from a semi-random comparison graph with a monotone adversary.
method Developed a weighted maximum likelihood estimator (MLE) and an SDP-based approach to reweight the semi-random graph.
result Achieves near-optimal sample complexity, up to a log^2(n) factor, for identifying the top-K preferred items.
Unified framework evaluates different nearest neighbor classification methods.
problem Evaluating and comparing classical, fuzzy, and fuzzy rough nearest neighbor classification methods.
method Standardized nearest neighbor weighting with kernel functions applied to distance and/or rank values of nearest neighbors.
result NN, FNN, and FRNN perform best with Boscovich distance, and NN and FRNN perform best with specific combinations of weights and scaling measures.
New method improves tensor completion by selectively preserving important elements.
problem Recovering corrupted high-dimensional tensor data with missing entries and noise.
method Tensor weighted correlated total variation (TWCTV) regularizer with ADMM algorithm.
result Superior performance in image completion, denoising, and background subtraction tasks.
This paper extends the Gaussian process interpretation of deep networks to more varied weight distributions.
problem Understanding the impact of different weight initialization schemes on deep learning dynamics.
method Extending the Gaussian process interpretation to PSEUDO-IID weight distributions, including sparse and low-rank networks.
result PSEUDO-IID initialized networks are effectively equivalent up to variance, enabling tractable posterior distributions.
PLD distills knowledge using choice-theoretic Plackett-Luce model.
problem Model compression and knowledge transfer between large and small networks.
method PLD uses a weighted list-wise ranking loss based on the Plackett-Luce model.
result PLD achieves consistent gains across diverse architectures and distillation methods.
LaLoRA prevents forgetting in LoRA fine-tuning.
problem Catastrophic forgetting in fine-tuned models.
method LaLoRA applies Laplace approximation to LoRA weights for regularization.
result Improved learning-forgetting trade-off with controllable regularization strength.
Paper proposes CounterSample to improve convergence in LTR models.
problem Large variance in IPS weights slows convergence in LTR models.
method Introduces CounterSample algorithm with provably better convergence.
result CounterSample converges faster than standard IPS-weighted methods.
Retrieving the most similar objects in a large-scale database for a given query is a fundamental building block in many application domains, ranging from web searches, visual, cross media, and document retrievals. State-of-the-art approaches have mainly focused on capturing the underlying geometry of the data manifolds…
Reverse-weighted portfolios outperform in commodity futures markets.
problem Efficiency of commodity futures markets.
method Permutation-weighted portfolios, rank-based methods.
result Reverse-weighted portfolio outperforms price-weighted portfolio.
New method for initializing low-rank neural networks improves performance.
problem Training low-rank neural networks efficiently and accurately.
method Inspired by function approximation, proposes a novel low-rank initialization framework.
result Demonstrates significant gap between spectral and low-rank initialization approaches.
Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.