Paper explores how knowledge distillation transfers inductive biases between models.
problem Transferring inductive biases between models for tasks with limited data.
method Knowledge distillation applied to models with different inductive biases (LSTMs vs. Transformers, CNNs vs. MLPs).
result Effect of inductive biases is transferred through knowledge distillation, impacting both performance and solution characteristics.
New method quantifies inductive bias for machine learning tasks.
problem Quantifying the amount of inductive bias in machine learning models.
method Estimates inductive bias by modeling loss distribution of random hypotheses.
result Higher dimensional tasks require greater inductive bias.
Interpolated-MLPs control inductive bias for better performance in low-compute tasks.
problem Low-compute performance gap between MLPs and CNNs.
method Introduced Interpolated MLP (I-MLP) approach to control inductive bias incrementally.
result Continuous logarithmic relationship between inductive bias and performance in low-compute tasks.
This research formalizes inductive generalization and proposes a new learning paradigm called Inductive Learning.
problem Generalization from easy to hard tasks, especially out-of-domain generalization.
method Formalizes inductive generalization, introduces Inductive Learning, and outlines steps to adapt techniques for learning model successors.
result A new learning paradigm (Inductive Learning) that emphasizes induction and universal properties of learning and computation.
Strong inductive biases prevent harmless interpolation in overparameterized models.
problem Understanding the conditions under which overparameterized models can interpolate noise without overfitting.
method Theoretical analysis of high-dimensional kernel regression and deep neural networks, focusing on the role of inductive biases.
result The strength of an estimator's inductive bias determines whether interpolation is harmless or requires fitting noise for good generalization.
New approach relaxes inductive biases of physics-inspired NNs for better performance.
problem Challenges in applying physics-inspired NNs to real-world systems.
method Examined and relaxed inductive biases of Hamiltonian NNs, improving performance on non-conservative systems.
result Improved performance on practical, non-conservative systems by relaxing inductive biases.
Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.
problem The impact of noise on interpolating models with strong inductive biases.
method Analyzing linear and classification models with sparse ground truths, proving fast rates for interpolators.
result Strong inductive biases can lead to faster but noisier interpolators, contrary to intuition.
I-BERT extends Transformer's self-attention to arbitrary input lengths.
problem Transformer models struggle with inductive generalization to unseen input lengths.
method Replaces positional encodings with a recurrent layer.
result I-BERT achieves state-of-the-art results on algorithmic tasks.
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…
Study links neural network inductive bias, feature learning, and generalization on Boolean functions.
problem Understanding how neural networks learn and generalize on Boolean data.
method End-to-end analysis of depth-2 discrete fully connected networks and DNF formulas, using Monte Carlo learning.
result Predictable training dynamics and interpretable features emerge, linking inductive bias and generalization.
Novel approach trains LLMs for inductive reasoning using probabilistic programs.
problem Training LLMs for inductive reasoning with sparse, ambiguous data.
method Program-based Posterior Training (PPT) using probabilistic inference.
result Significant improvement in estimation accuracy and alignment with human judgments.
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the compositional logical rules underlying the knowledge graph, and they are limited …
Integrates inductive biases into VAEs using intermediary latent variables.
problem Ineffective mechanisms for incorporating inductive biases into VAEs.
method InteL-VAEs use an intermediary latent space to control encoding, with a parametric function to enforce desired properties.
result InteL-VAEs lead to better generative models and representations.
R2N learns interpretable rules and literals from numerical features.
problem Lack of expressive vocabulary in rule-based decision models.
method Relational Rule Network (R2N) learns literals and rules end-to-end.
result Learned literals improve prediction accuracy and rule conciseness.
Novel approach uses inductive biases for semiconductor etching.
problem Significant violations of physics in etching process predictions.
method Introduced deep learning model with inductive biases.
result Fits measurements faster and follows physical behavior.
One-layer transformers can't solve induction heads task efficiently.
problem Solving the induction heads task efficiently with one-layer transformers.
method Communication complexity argument showing exponential size requirement.
result No one-layer transformer can solve the induction heads task efficiently.
We propose an inductive matrix completion model without using side information. By factorizing the (rating) matrix into the product of low-dimensional latent embeddings of rows (users) and columns (items), a majority of existing matrix completion methods are transductive, since the learned embeddings cannot generalize …
Transformers learn rich in-context dependencies efficiently.
problem Understanding how transformers learn long-range dependencies efficiently.
method Approximation and dynamics analysis of induction head mechanisms.
result Abrupt transition from lazy to rich mechanisms during training.
OTI extends OTP for inductive semi-supervised learning.
problem Inductive semi-supervised learning for out-of-sample data.
method Optimal transport-based approach extended to inductive tasks.
result OTI outperforms state-of-the-art methods in experiments.
Model proposes neural network for continuous time dynamics with inductive biases.
problem Training neural networks for small datasets with nonlinear dynamics.
method Inductive biases on decay rates and frequencies using Koopman operator theory.
result Higher forecasting performance with single short training sequence.
DEAL model predicts links for new nodes with only attribute info.
problem Predicting links for new nodes with only attribute info.
method DEAL model with two encoders and alignment mechanism.
result DEAL significantly outperforms existing methods on inductive link prediction.
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 shows different trajectory prediction models generalize better under OoD conditions.
problem Comparing trajectory prediction models' robustness across different datasets.
method Training models on Argoverse 2 and testing on Waymo Open Motion, and vice versa, with various augmentation strategies.
result Smallest model with highest inductive bias performs best in OoD generalization.
Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning. While "model-based" BRL algorithms have focused either on maintaining a posterior distribution on models or value functions and combining this with approximate dynamic programming or tree search, previous Bayesian "mo…
We introduce several methods to define the self-inductance of a single loop as the regularization of divergent integrals which we obtain by applying Neumann (or Weber) formula for the mutual inductance of a pair of loops to the case when two loops are identical.
This paper explains the theoretical inductive bias of Isolation Forest.
problem Lack of theoretical foundation explaining Isolation Forest's success.
method Formulated the growth process of iForest as a random walk, derived expected depth function using transition probabilities.
result Established a theoretical understanding of iForest's effectiveness and parameter adaptability.
Transformers learn to use induction heads or shortcuts based on data diversity.
problem How data diversity influences the behavior of transformers.
method Gradient-based training of a single-layer transformer on a minimal task.
result Data diversity steers transformers toward induction heads or shortcuts.
We introduce the notion of large scale inductive dimension for asymptotic resemblance spaces. We prove that the large scale inductive dimension and the asymptotic dimensiongrad are equal in the class of r-convex metric spaces. This class contains the class of all geodesic metric spaces and all finitely generated groups…
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed when the system configuration changes. The resulting inefficiency in terms of da…
PAC-Net prunes deep models for better transfer learning.
problem Improving transfer learning with over-parameterized models.
method Prune, Allocate, Calibrate (PAC) approach.
result PAC-Net achieves state-of-the-art performance in inductive transfer learning.
Extract symbolic models from deep learning with inductive biases.
problem Interpreting and discovering physical principles from deep neural networks.
method Introduce strong inductive biases in GNNs, encourage sparse latent representations, apply symbolic regression.
result Extracted symbolic equations from neural networks, including known force laws and new analytic formulas.
Proposes a neural framework to select subsets efficiently across different models.
problem Lack of generalizability in subset selection methods for unseen architectures.
method Introduces a trainable subset selection framework, SubSelNet, that uses attention-based neural gadgets and subset samplers.
result SubSelNet generalizes across architectures and outperforms existing methods.
Improved stability and generalization for blackbox learned optimizers.
problem Stability and generalization issues in blackbox learned optimizers.
method Investigation using dynamical systems, modifications to optimizer architecture and meta-training procedure.
result Improved stability and generalization of learned optimizers.
If p:Y→X is an unramified covering map between two compact oriented surfaces of genus at least two, then it is proved that the embedding map, corresponding to p, from the Teichmüller space T(X), for X, to T(Y) actually extends to an embedding between the Thurston compactification of the tw…
We describe our language-independent unsupervised word sense induction system. This system only uses topic features to cluster different word senses in their global context topic space. Using unlabeled data, this system trains a latent Dirichlet allocation (LDA) topic model then uses it to infer the topics distribution…
IMM generates high-quality samples in few steps with stable training.
problem Slow inference and instability in generating high-quality samples using diffusion models and Flow Matching.
method Inductive Moment Matching (IMM) is a new generative model for one- or few-step sampling with a single-stage training procedure.
result IMM achieves state-of-the-art 2-step FID of 1.98 on CIFAR-10 for a model trained from scratch.
Rule-based models are often used for data analysis as they combine interpretability with predictive power. We present RuleKit, a versatile tool for rule learning. Based on a sequential covering induction algorithm, it is suitable for classification, regression, and survival problems. The presence of a user-guided induc…
GTEA learns node representations in temporal interaction graphs.
problem Inductive representation learning on temporal interaction graphs.
method Integrates sequence model with time encoder and self-attention scheme for edge and node embeddings.
result GTEA learns comprehensive node representations capturing temporal and structural characteristics.
Inspired by the possibility that generative models based on quantum circuits can provide a useful inductive bias for sequence modeling tasks, we propose an efficient training algorithm for a subset of classically simulable quantum circuit models. The gradient-free algorithm, presented as a sequence of exactly solvable …
We consider the problem of quickest change-point detection in data streams. Classical change-point detection procedures, such as CUSUM, Shiryaev-Roberts and Posterior Probability statistics, are optimal only if the change-point model is known, which is an unrealistic assumption in typical applied problems. Instead we p…
New methods for CI testing under model misspecification.
problem Challenges in CI testing with misspecified models.
method Proposes new approximations and upper bounds for testing errors of regression-based CI tests.
result Introduces the Rao-Blackwellized Predictor Test (RBPT) robust against misspecified inductive biases.
NNLMs optimize poorly for word probabilities due to embedding space structure.
problem NNLMs assign suboptimal probabilities to some words.
method Analyzed the inductive bias of NNLMs and the structure of word embeddings.
result Words on the convex hull have bounded probability, affecting others.
Soft geometric bias improves physical dynamics predictions.
problem Learning physical dynamics with exact group equivariance can degrade performance.
method Object-centric world models using geometric algebra neural networks.
result Soft geometric inductive bias leads to better physical fidelity predictions.
We prove addition and subspace theorems for asymptotic large inductive dimension. We investigate a transfinite extension of this dimension and show that it is trivial.
Extends positive mass theorem to arbitrary dimensions using a new inductive scheme.
problem Overcoming singularities in the Schoen-Yau proof for arbitrary dimensions.
method Inductive scheme combining shielding principle, conformal blow-up, and Cheeger-Naber bound.
result Proof of positive mass theorem in arbitrary dimensions.
We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a representation-based approach (Artetxe et al., 2017). To train the model, we derive an efficient Viterbi EM algorithm. We provide empiric…
ExpBERT uses natural language explanations to improve text interpretation.
problem Improving text interpretation for relation extraction tasks.
method Fine-tuning BERT on MultiNLI to interpret natural language explanations.
result ExpBERT matches a BERT baseline but requires less labeled data and improves performance.
The local induction equation, or the binormal flow on space curves is a well-known model of deformation of space curves as it describes the dynamics of vortex filaments, and the complex curvature is governed by the nonlinear Schrödinger equation. In this paper, we present its discrete analogue, namely, a model of defor…