Researcher Evidence Record
Matus Telgarsky
This bounded record lists 43 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.LG, cs.GT, cs.DS work dated 2009 to 2026. The record describes sources and coverage; it makes no judgment about the person.
Compiled coverage vector
A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.
Attributed works
A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.
-
2026 Pith paper
Understanding Reasoning from Pretraining to Post-Training
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 6
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
One-layer transformers fail to solve the induction heads task
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
Spectrum Extraction and Clipping for Implicitly Linear Layers
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
Transformers, parallel computation, and logarithmic depth
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 7 pith inbound references from cited_work_pith_inbound_counts
-
2023 Pith paper
On Achieving Optimal Adversarial Test Error
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2023 Pith paper
Representational Strengths and Limitations of Transformers
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 12 external cited by from arxiv_reference
- 5 pith inbound references from cited_work_pith_inbound_counts
-
2022 Pith paper
Feature selection with gradient descent on two-layer networks in low-rotation regimes
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 1 pith inbound references from cited_work_pith_inbound_counts
-
2022 Pith paper
Stochastic linear optimization never overfits with quadratically-bounded losses on general data
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Actor-critic is implicitly biased towards high entropy optimal policies
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Fast Margin Maximization via Dual Acceleration
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Early-stopped neural networks are consistent
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Generalization bounds via distillation
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 2 pith inbound references from cited_work_pith_inbound_counts
-
2020 Pith paper
Gradient descent follows the regularization path for general losses
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2020 Pith paper
Directional convergence and alignment in deep learning
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2019 Pith paper
Neural tangent kernels, transportation mappings, and universal approximation
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2019 Pith paper
Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 2 pith inbound references from cited_work_pith_inbound_counts
-
2019 Pith paper
Approximation power of random neural networks
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2019 Pith paper
Characterizing the implicit bias via a primal-dual analysis
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2019 Pith paper
A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2018 Pith paper
Size-Noise Tradeoffs in Generative Networks
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2018 Pith paper
Gradient descent aligns the layers of deep linear networks
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 22 external cited by from pith
- 9 pith inbound references from cited_work_pith_inbound_counts
-
2018 Pith paper
Risk and parameter convergence of logistic regression
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 5 pith inbound references from cited_work_pith_inbound_counts
-
2017 Pith paper
Social welfare and profit maximization from revealed preferences
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2017 Pith paper
Spectrally-normalized margin bounds for neural networks
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 174 external cited by from pith
- 4 pith inbound references from cited_work_pith_inbound_counts
-
2017 Pith paper
Neural networks and rational functions
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2017 Pith paper
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 3 pith inbound references from cited_work_pith_inbound_counts
-
2016 Pith paper
Greedy bi-criteria approximations for $k$-medians and $k$-means
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2016 Pith paper
Benefits of depth in neural networks
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2015 Pith paper
Rate of Price Discovery in Iterative Combinatorial Auctions
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2015 Pith paper
Representation Benefits of Deep Feedforward Networks
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 6 pith inbound references from cited_work_pith_inbound_counts
-
2015 Pith paper
Convex Risk Minimization and Conditional Probability Estimation
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2014 Pith paper
Scalable Nonlinear Learning with Adaptive Polynomial Expansions
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2013 Pith paper
Moment-based Uniform Deviation Bounds for $k$-means and Friends
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2013 Pith paper
Boosting with the Logistic Loss is Consistent
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2013 Pith paper
Margins, Shrinkage, and Boosting
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2013 Pith paper
Dirichlet draws are sparse with high probability
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2012 Pith paper
Tensor decompositions for learning latent variable models
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 1 pith inbound references from cited_work_pith_inbound_counts
-
2012 Pith paper
Statistical Consistency of Finite-dimensional Unregularized Linear Classification
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2011 Pith paper
Blackwell Approachability and Minimax Theory
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2011 Pith paper
A Primal-Dual Convergence Analysis of Boosting
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2009 Pith paper
Central Binomial Tail Bounds
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Matus Telgarsky
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
Evidence apparatus
The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.
| Lane | State | Observed | Boundary and source |
|---|---|---|---|
| identity | Measured | 2 | Canonical identity row plus public typed identifiers. source=authors, author_identifiers |
| papers | Measured | 43 of 43 bounded rows | Rows attributed to this author UUID in the Pith corpus. source=paper_authors |
| works | Measured zero | 0 of 0 bounded rows | Imported works not duplicated by the paper ledger. source=author_works |
| reviews | Measured | 1 of 43 bounded rows | Coverage count only. No review outcome is projected onto the person. source=current_verdicts |
| citations | Measured | 11 of 43 bounded rows | Counts remain itemized by work and source. source=cited_works |
| coauthors | Measured | 40 of 43 bounded rows | Shared-work edges from admitted paper rows. source=paper_authors |
| account | Unavailable | No public count of 1 bounded rows | Account metadata is separate from corpus evidence. source=users.author_id |
Public identity sources
-
name variant
Matus Telgarsky
Enumerated research scope
- cs.LG38 rows
- cs.GT3 rows
- cs.DS1 rows
- math.PR1 rows
- 20091 rows
- 20112 rows
- 20122 rows
- 20134 rows
- 20141 rows
- 20153 rows
- 20162 rows
- 20174 rows
- 20183 rows
- 20195 rows
- 20202 rows
- 20214 rows
- 20222 rows
- 20232 rows
- 20244 rows
- 20251 rows
- 20261 rows
Record scope
The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.
Paper findings remain attached to papers. They do not become findings about this researcher.
Self-published account annex
Linked Pith account
Unavailable No public Pith account is linked to this corpus identity.
The account lane is self-published. Linking proves account control only and changes no corpus fact.