Papers

Field

Top tools here

Open problems in Graph learning

Quantization error propagation in recurrent states1 paper raises it · 1 addresses it
Low-precision recurrent states in linear attention degrade accuracy due to error accumulation over time and across dimensions.
- STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantizationraises · addresses
Train-rollout discrepancy in low-precision RL1 paper raises it · 1 addresses it
Quantization in RL training and rollout paths can diverge, reducing the effectiveness of low-precision methods.
- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Modelsraises · addresses
Distribution shift in decoding-aware pruning1 paper raises it · 1 addresses it
Pruning guided by natural sequences fails to account for self-generated token distributions during decoding, hurting performance.
- SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inferenceraises · addresses
Lack of benchmarks for graph decision-making in System One models1 paper raises it · 1 addresses it
Existing benchmarks do not adequately evaluate System One models on graph tasks, limiting progress in this area.
- GraphDecisionBench: Benchmarking System One Models on Graph Tasksraises · addresses
Error propagation in low-rank weight factorization1 paper raises it · 1 addresses it
Local criteria for subspace selection ignore global error propagation, leading to performance collapse at high compression.
- Learning Functional Subspaces for Neural Network Compressionraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

gradient descent · learning rate · neural networks233 papers40 this week
graph learning · graph neural · graph neural networks269 papers30 this week
neural networks · neural network · arnold networks155 papers30 this week
memory efficient · optimizers · low rank adaptation164 papers26 this week
bit quantization · quantization aware training · quantization aware158 papers18 this week
linear attention · softmax attention · transformer attention108 papers10 this week

Topics in this field

Active contributors · 90 days

Pietro LiòLocaLeJEPA: Maximum Entropy Representations under Geometric Priors8
Dan AlistarhWhat Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes6
Rong-Hua LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Xunkai LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Rebekka BurkholzAC/DC on a Budget - Alternating Sparse Phases5
Haggai MaronGraph Metanetworks for Transformer Based Language Models5

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGSep 29
Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training
Zixuan Gong, Zeyu Gan, Jiaye Teng, Yong Liu
Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram representation, we observe that it jointly processes marginal-scale and interaction information. This opens an alternative way to organize geometric information hierarchically, motivating the Normalize-Then-Precondition framework. Specifically, it first uses diagonal-Gram information to construct a marginally normalized update, then applies spectral preconditioning to its directional interaction geometry. Building on this framework, we develop NormPre with NormPre-G and NormPre-L adopting global and localized spectral preconditioning, grounded in spectral-norm steepest descent and a regularized formulation followed by leading mode selection, respectively. To enable large-scale training, NormPre-G uses Newton-Schulz iterations and NormPre-L employs randomized sketching to approximate the leading interaction eigenspace. Theoretically, we establish $\mathcal{O}(T^{-1/2})$ convergence guarantees for simplified versions of NormPre. Across extensive pretraining experiments on GPT-2 Small, LLaMA and Qwen3, both variants consistently outperform…
PDF arXiv
arXiv cs.LGSep 29
AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization
Pengyu He, Yan Zhang, Ruien Li, Guangwen Yang
The pre-training of Large Language Models (LLMs) is increasingly conducted across multiple data centers. As training scales to a larger number of accelerators, the fraction of time spent on computation decreases, while the fraction spent on communication increases. Therefore, frequent synchronization becomes a growing bottleneck. Local update methods reduce this cost by allowing workers to perform several optimizer steps between synchronizations. Most local update methods set the number of local optimizer steps between synchronizations before training and keep this interval fixed throughout the run. However, the best interval can change during the entire train process. If the interval and optimizer are adapted to the current training state, the communication frequency is reduced while maintaining the training performance. In this work, we introduce AutoLoCo, an adaptive training framework to reduce communication in LLM training. It adapts the local interval using scalar training statistics and corrects each outer update. Our method is motivated by two observations: 1) the appropriate local interval varies across training stages, and 2) changing the number of inner steps per…
PDF arXiv
arXiv cs.LGSep 29
Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
Ruiyi Ding, Jie Li, Kang He, Ziyan Liu, Chengru Song +2
Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with only a few bits. Such formats use a scale to map floating-point values into a small codebook; NVFP4 improves local range utilization by letting every 16 E2M1 weights share an E4M3 block scale. Choosing that scale is difficult in GPTQ because quantizing one column updates those that follow, so evaluating a block independently can misestimate its final reconstruction error. Large models pose a second challenge: full-precision weights, calibration activations, and second-order state cannot all remain on one accelerator, while assigning complete layers to devices leaves each time-consuming layer solve serial. We introduce \emph{Schur Replay}, a scale-selection algorithm that reproduces the GPTQ updates caused by each block scale and scores the resulting block error after accounting for compensation from unquantized columns. Separately, our execution infrastructure keeps only the active layer resident, tiers activations across device, host, and disk, retires full-precision layers after export, and distributes independent output rows…
PDF arXiv
arXiv cs.LGSep 29
Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters
Zhaoxian Wu, Tayfun Gokmen, Omobayode Fagbohungbe, T. Patrick Xiao, Tianyi Chen
Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, scaling AIMC to train modern deep models remains an open challenge due to severe hardware non-idealities, including physical weights with finite dynamic range and write granularity, analog-digital converters with finite resolution, and noisy and asymmetric updates. Guided by the insight that gradient accumulation is sensitive to precision and rounding errors, we adopt a mixed-precision training paradigm: executing forward and backward matrix multiplications in the analog domain while computing weight gradients in the digital domain. To enable scalable training, we present a holistic system-algorithm co-design that co-optimizes weight mapping to ensure well-conditioned physical and logical weight profiles, couples a preconditioned optimizer with threshold-triggered open-loop pulsing to stabilize training trajectories, and aligns converter dynamic ranges to suppress quantization errors. Evaluated via hardware-calibrated architectural simulations calibrated with electrochemical RAM measurements, our framework scales Transformer…
PDF arXiv
arXiv cs.LGSep 29
Theory on Attention Dynamics for Out-of-Distribution In-Context Learning
Junze Deng, Daouda Sow, Sen Lin, Yingbin Liang
Transformers have demonstrated remarkable in-context learning (ICL) capabilities, enabling them to perform new tasks without additional fine-tuning. However, their performance often deteriorates when encountering out-of-distribution (OOD) inputs that deviate from the training distribution, and the underlying theory remains poorly understood. To fill this gap, we characterize the OOD error under the input distribution shift through the interplay between the dynamics of the so-called $α$-type and $β$-type attention weights, which represent the transformer's confidence in identifying the correct and incorrect features, respectively. Our results indicate that the OOD error for each feature depends on all pairwise interactions between the training features and OOD features, and under certain cases the transformer performs no better than random guessing. To improve the OOD generalization performance, we next investigate the impact of model finetuning with the OOD data, and particularly, characterize the model forgetting performance on the source domain. Interestingly, the performance on the source domain may not always degrade after finetuning, which highly depends on the nature of the…
PDF arXiv
arXiv cs.LGSep 28
Reducing the Adaptation Gap Through Reachable Fisher Geometry
Wasif Jalal, Sachin Deb, Asif Salekin
Parameter-efficient fine-tuning (PEFT) determines not only how many parameters are trained, but also which local directions a model can move in, so similar adapters can affect subgroup losses differently. Since curvature matrices are infeasible to form at adapter scale, scalar summaries such as the Fisher trace are often used instead. We study what the trace reveals and what it loses through the reachable Fisher: each subgroup's full-model Fisher pulled back through the adapter Jacobian. Under likelihood losses, it represents the Gauss-Newton curvature accessible to the adapter, and its trace can be computed from score-gradient norms without forming the full matrix. Under matched subgroup gradients, a positive-definite reachable-Fisher difference, with a margin exceeding the Hessian-Fisher defect, implies that every sufficiently small nonzero model-changing update increases the signed gap. In contrast, the restricted operator norm determines worst-case quadratic change, while a matrix-free Frobenius discrepancy bounds its reachable-Fisher component. Trace alone cannot certify definiteness or control matrix mismatch. Equal traces rule out a positive-definite difference but can…
PDF arXiv

Papers

Topics in this field

gradient descent · learning rate · neural networks233 papers40 this week
graph learning · graph neural · graph neural networks269 papers30 this week
neural networks · neural network · arnold networks155 papers30 this week
memory efficient · optimizers · low rank adaptation164 papers26 this week
bit quantization · quantization aware training · quantization aware158 papers18 this week
linear attention · softmax attention · transformer attention108 papers10 this week

Active contributors · 90 days

Pietro LiòLocaLeJEPA: Maximum Entropy Representations under Geometric Priors8
Dan AlistarhWhat Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes6
Rong-Hua LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Xunkai LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Rebekka BurkholzAC/DC on a Budget - Alternating Sparse Phases5
Haggai MaronGraph Metanetworks for Transformer Based Language Models5

Recent papers

All papers in Research

arXiv cs.LGSep 29
Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training
Zixuan Gong, Zeyu Gan, Jiaye Teng, Yong Liu
Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram representation, we observe that it jointly processes marginal-scale and interaction information. This opens an alternative way to organize geometric information hierarchically, motivating the Normalize-Then-Precondition framework. Specifically, it first uses diagonal-Gram information to construct a marginally normalized update, then applies spectral preconditioning to its directional interaction geometry. Building on this framework, we develop NormPre with NormPre-G and NormPre-L adopting global and localized spectral preconditioning, grounded in spectral-norm steepest descent and a regularized formulation followed by leading mode selection, respectively. To enable large-scale training, NormPre-G uses Newton-Schulz iterations and NormPre-L employs randomized sketching to approximate the leading interaction eigenspace. Theoretically, we establish $\mathcal{O}(T^{-1/2})$ convergence guarantees for simplified versions of NormPre. Across extensive pretraining experiments on GPT-2 Small, LLaMA and Qwen3, both variants consistently outperform…
PDF arXiv
arXiv cs.LGSep 29
AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization
Pengyu He, Yan Zhang, Ruien Li, Guangwen Yang
The pre-training of Large Language Models (LLMs) is increasingly conducted across multiple data centers. As training scales to a larger number of accelerators, the fraction of time spent on computation decreases, while the fraction spent on communication increases. Therefore, frequent synchronization becomes a growing bottleneck. Local update methods reduce this cost by allowing workers to perform several optimizer steps between synchronizations. Most local update methods set the number of local optimizer steps between synchronizations before training and keep this interval fixed throughout the run. However, the best interval can change during the entire train process. If the interval and optimizer are adapted to the current training state, the communication frequency is reduced while maintaining the training performance. In this work, we introduce AutoLoCo, an adaptive training framework to reduce communication in LLM training. It adapts the local interval using scalar training statistics and corrects each outer update. Our method is motivated by two observations: 1) the appropriate local interval varies across training stages, and 2) changing the number of inner steps per…
PDF arXiv
arXiv cs.LGSep 29
Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
Ruiyi Ding, Jie Li, Kang He, Ziyan Liu, Chengru Song +2
Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with only a few bits. Such formats use a scale to map floating-point values into a small codebook; NVFP4 improves local range utilization by letting every 16 E2M1 weights share an E4M3 block scale. Choosing that scale is difficult in GPTQ because quantizing one column updates those that follow, so evaluating a block independently can misestimate its final reconstruction error. Large models pose a second challenge: full-precision weights, calibration activations, and second-order state cannot all remain on one accelerator, while assigning complete layers to devices leaves each time-consuming layer solve serial. We introduce \emph{Schur Replay}, a scale-selection algorithm that reproduces the GPTQ updates caused by each block scale and scores the resulting block error after accounting for compensation from unquantized columns. Separately, our execution infrastructure keeps only the active layer resident, tiers activations across device, host, and disk, retires full-precision layers after export, and distributes independent output rows…
PDF arXiv
arXiv cs.LGSep 29
Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters
Zhaoxian Wu, Tayfun Gokmen, Omobayode Fagbohungbe, T. Patrick Xiao, Tianyi Chen
Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, scaling AIMC to train modern deep models remains an open challenge due to severe hardware non-idealities, including physical weights with finite dynamic range and write granularity, analog-digital converters with finite resolution, and noisy and asymmetric updates. Guided by the insight that gradient accumulation is sensitive to precision and rounding errors, we adopt a mixed-precision training paradigm: executing forward and backward matrix multiplications in the analog domain while computing weight gradients in the digital domain. To enable scalable training, we present a holistic system-algorithm co-design that co-optimizes weight mapping to ensure well-conditioned physical and logical weight profiles, couples a preconditioned optimizer with threshold-triggered open-loop pulsing to stabilize training trajectories, and aligns converter dynamic ranges to suppress quantization errors. Evaluated via hardware-calibrated architectural simulations calibrated with electrochemical RAM measurements, our framework scales Transformer…
PDF arXiv
arXiv cs.LGSep 29
Theory on Attention Dynamics for Out-of-Distribution In-Context Learning
Junze Deng, Daouda Sow, Sen Lin, Yingbin Liang
Transformers have demonstrated remarkable in-context learning (ICL) capabilities, enabling them to perform new tasks without additional fine-tuning. However, their performance often deteriorates when encountering out-of-distribution (OOD) inputs that deviate from the training distribution, and the underlying theory remains poorly understood. To fill this gap, we characterize the OOD error under the input distribution shift through the interplay between the dynamics of the so-called $α$-type and $β$-type attention weights, which represent the transformer's confidence in identifying the correct and incorrect features, respectively. Our results indicate that the OOD error for each feature depends on all pairwise interactions between the training features and OOD features, and under certain cases the transformer performs no better than random guessing. To improve the OOD generalization performance, we next investigate the impact of model finetuning with the OOD data, and particularly, characterize the model forgetting performance on the source domain. Interestingly, the performance on the source domain may not always degrade after finetuning, which highly depends on the nature of the…
PDF arXiv
arXiv cs.LGSep 28
Reducing the Adaptation Gap Through Reachable Fisher Geometry
Wasif Jalal, Sachin Deb, Asif Salekin
Parameter-efficient fine-tuning (PEFT) determines not only how many parameters are trained, but also which local directions a model can move in, so similar adapters can affect subgroup losses differently. Since curvature matrices are infeasible to form at adapter scale, scalar summaries such as the Fisher trace are often used instead. We study what the trace reveals and what it loses through the reachable Fisher: each subgroup's full-model Fisher pulled back through the adapter Jacobian. Under likelihood losses, it represents the Gauss-Newton curvature accessible to the adapter, and its trace can be computed from score-gradient norms without forming the full matrix. Under matched subgroup gradients, a positive-definite reachable-Fisher difference, with a margin exceeding the Hessian-Fisher defect, implies that every sufficiently small nonzero model-changing update increases the signed gap. In contrast, the restricted operator norm determines worst-case quadratic change, while a matrix-free Frobenius discrepancy bounds its reachable-Fisher component. Trace alone cannot certify definiteness or control matrix mismatch. Equal traces rule out a positive-definite difference but can…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 2m ago

Graph learning

Found by the topic model: graph learning, gradient descent, bit quantization.

154papers this week−30.0% vs last week

All papers · 1.1k With code · 11

Newest Most relevant

1k papers this month

Open problems in Graph learning

Quantization error propagation in recurrent states1 paper raises it · 1 addresses it
Low-precision recurrent states in linear attention degrade accuracy due to error accumulation over time and across dimensions.
- STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantizationraises · addresses
Train-rollout discrepancy in low-precision RL1 paper raises it · 1 addresses it
Quantization in RL training and rollout paths can diverge, reducing the effectiveness of low-precision methods.
- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Modelsraises · addresses
Distribution shift in decoding-aware pruning1 paper raises it · 1 addresses it
Pruning guided by natural sequences fails to account for self-generated token distributions during decoding, hurting performance.
- SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inferenceraises · addresses
Lack of benchmarks for graph decision-making in System One models1 paper raises it · 1 addresses it
Existing benchmarks do not adequately evaluate System One models on graph tasks, limiting progress in this area.
- GraphDecisionBench: Benchmarking System One Models on Graph Tasksraises · addresses
Error propagation in low-rank weight factorization1 paper raises it · 1 addresses it
Local criteria for subspace selection ignore global error propagation, leading to performance collapse at high compression.
- Learning Functional Subspaces for Neural Network Compressionraises · addresses

Named by an AI from these papers' abstracts.