Pith. sign in

REVIEW 12 cited by

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.08799 v3 pith:PW4XVOIW submitted 2022-07-18 cs.LG cs.NEmath.OCstat.ML

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

classification cs.LG cs.NEmath.OCstat.ML
keywords learningsparsetrainingcomputationaldeephiddenmodelparities
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some accounts of how these resources modulate statistical capacity, far less is known about their effect on the computational problem of model training. This work conducts such an exploration through the lens of learning a $k$-sparse parity of $n$ bits, a canonical discrete search problem which is statistically easy but computationally hard. Empirically, we find that a variety of neural networks successfully learn sparse parities, with discontinuous phase transitions in the training curves. On small instances, learning abruptly occurs at approximately $n^{O(k)}$ iterations; this nearly matches SQ lower bounds, despite the apparent lack of a sparse prior. Our theoretical analysis shows that these observations are not explained by a Langevin-like mechanism, whereby SGD "stumbles in the dark" until it finds the hidden set of features (a natural algorithm which also runs in $n^{O(k)}$ time). Instead, we show that SGD gradually amplifies the sparse solution via a Fourier gap in the population gradient, making continual progress that is invisible to loss and error metrics.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Progress measures for grokking via mechanistic interpretability

    cs.LG 2023-01 accept novelty 8.0

    Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.

  2. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

    cs.LG 2022-11 conditional novelty 8.0

    GPT-2 small solves indirect object identification via a circuit of 26 attention heads organized into seven functional classes discovered through causal interventions.

  3. Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity

    cs.LG 2026-06 unverdicted novelty 7.0

    Dead-Direction Signatures provide closed-form spectral readings of dead directions in network activations and gradients that track rank deficits at singular minima, offering a cheap directional alternative to SGLD-based LLC.

  4. Dead Directions: Geometric Singular Learning

    cs.LG 2026-06 unverdicted novelty 7.0

    Dead directions recover Watanabe's RLCT contribution and triple (λ, m, ν) from directional Fisher curvature decay rates in original parameter space for singular models, extended via K-FAC to networks and gauge-equivar...

  5. The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently

    cs.LG 2026-05 unverdicted novelty 7.0

    Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.

  6. The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

    cs.LG 2026-03 unverdicted novelty 7.0

    The grokking delay in encoder-decoder models on one-step Collatz prediction stems from decoder inability to use early-learned encoder representations of parity and residue structure, with numeral base acting as a stro...

  7. Massive Activations in Large Language Models

    cs.CL 2024-02 unverdicted novelty 7.0

    Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.

  8. Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

    cs.LG 2026-07 accept novelty 6.0

    In a fully tractable 12K Llama-style model, grokking is a conditional fragile phase transition gated by coverage (tracking modulus more than structure), weight decay, and floating-point reduction order, so evidence mu...

  9. Tracking Representation Dynamics in Large Language Models with Persistent Homology

    cs.LG 2026-06 unverdicted novelty 6.0

    Persistent homology analysis of LLM activations shows most topological reorganization occurs early in fine-tuning, with a transient peak followed by stabilization and distinct trajectories for different alignment objectives.

  10. Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases

    cs.LG 2026-05 unverdicted novelty 6.0

    Repeating smaller datasets speeds up training via sampling biases that enable appropriate layer-wise growth, leading to compute savings over larger datasets across tasks and architectures.

  11. The two clocks and the innovation window: When and how generative models learn rules

    cs.LG 2026-05 unverdicted novelty 6.0

    Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.

  12. The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

    cs.LG 2026-03 unverdicted novelty 6.0

    Grokking delay on Collatz prediction is a decoder access bottleneck after early encoder structure learning, with numeral base as a strong inductive bias on learnability.